< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1073 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.6245. Min Act: -0.1700

Data Index: 3547901 (Open Web Text)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.5354. Min Act: -0.1700

Data Index: 6959716 (Open Web Text)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.5323. Min Act: -0.1700

Data Index: 8604278 (Open Web Text)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.5010. Min Act: -0.1700

Data Index: 6516219 (Open Web Text)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4912. Min Act: -0.1700

Data Index: 8025730 (Open Web Text)

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.5091. Min Act: -0.1700

Data Index: 8490635 (Open Web Text)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.5031. Min Act: -0.1700

Data Index: 8719991 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4794. Min Act: -0.1700

Data Index: 455402 (Open Web Text)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4928. Min Act: -0.1700

Data Index: 26055 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4815. Min Act: -0.1700

Data Index: 4100088 (Open Web Text)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4751. Min Act: -0.1700

Data Index: 4287579 (Open Web Text)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4693. Min Act: -0.1700

Data Index: 1476871 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4587. Min Act: -0.1700

Data Index: 1253019 (Open Web Text)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4402. Min Act: -0.1700

Data Index: 5045693 (Open Web Text)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4580. Min Act: -0.1700

Data Index: 4694690 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4564. Min Act: -0.1700

Data Index: 4408845 (Open Web Text)

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4497. Min Act: -0.1700

Data Index: 6215592 (Open Web Text)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4407. Min Act: -0.1700

Data Index: 3713114 (Open Web Text)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4370. Min Act: -0.1700

Data Index: 5491913 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6245. Min Range: -2.6245

Max Act: 2.4102. Min Act: -0.1700

Data Index: 5596458 (Open Web Text)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #19