< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 145 in Layer 1

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: 2.1292. Min Range: -2.1292

Max Act: 2.1292. Min Act: -0.1700

Data Index: 7478174 (Open Web Text)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.1094. Min Act: -0.1700

Data Index: 8778166 (Open Web Text)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0718. Min Act: -0.1700

Data Index: 4603173 (Open Web Text)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0667. Min Act: -0.1700

Data Index: 6109621 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0402. Min Act: -0.1700

Data Index: 1336531 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0202. Min Act: -0.1700

Data Index: 6098051 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0250. Min Act: -0.1700

Data Index: 1494682 (Open Web Text)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0122. Min Act: -0.1700

Data Index: 8730567 (Open Web Text)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0121. Min Act: -0.1700

Data Index: 6532623 (Open Web Text)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0019. Min Act: -0.1700

Data Index: 6489383 (Open Web Text)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1292. Min Range: -2.1292

Max Act: 2.0090. Min Act: -0.1700

Data Index: 1438791 (Open Web Text)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9802. Min Act: -0.1700

Data Index: 7715649 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9630. Min Act: -0.1700

Data Index: 6600883 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9453. Min Act: -0.1700

Data Index: 7199024 (Open Web Text)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9430. Min Act: -0.1700

Data Index: 5771619 (Open Web Text)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9496. Min Act: -0.1700

Data Index: 213826 (Open Web Text)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9460. Min Act: -0.1700

Data Index: 4585995 (Open Web Text)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9569. Min Act: -0.1700

Data Index: 4730852 (Open Web Text)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9290. Min Act: -0.1700

Data Index: 5748176 (Open Web Text)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1292. Min Range: -2.1292

Max Act: 1.9251. Min Act: -0.1700

Data Index: 3988055 (Open Web Text)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #19