< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1353 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: 2.1308. Min Range: -2.1308

Max Act: 2.1308. Min Act: -0.1700

Data Index: 2889735 (Open Web Text)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.1036. Min Act: -0.1700

Data Index: 1509328 (Open Web Text)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0680. Min Act: -0.1700

Data Index: 1333931 (Open Web Text)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0485. Min Act: -0.1700

Data Index: 4570707 (Open Web Text)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0433. Min Act: -0.1700

Data Index: 132121 (Open Web Text)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0326. Min Act: -0.1700

Data Index: 729905 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0200. Min Act: -0.1700

Data Index: 2036878 (Open Web Text)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0356. Min Act: -0.1700

Data Index: 7946711 (Open Web Text)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0446. Min Act: -0.1700

Data Index: 3722609 (Open Web Text)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0079. Min Act: -0.1700

Data Index: 3456629 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0243. Min Act: -0.1700

Data Index: 7298538 (Open Web Text)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0100. Min Act: -0.1700

Data Index: 7236244 (Open Web Text)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0142. Min Act: -0.1700

Data Index: 7532048 (Open Web Text)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0310. Min Act: -0.1700

Data Index: 7945239 (Open Web Text)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0430. Min Act: -0.1700

Data Index: 6378856 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0157. Min Act: -0.1700

Data Index: 7897396 (Open Web Text)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0027. Min Act: -0.1700

Data Index: 857295 (Open Web Text)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1308. Min Range: -2.1308

Max Act: 1.9985. Min Act: -0.1700

Data Index: 6756121 (Open Web Text)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1308. Min Range: -2.1308

Max Act: 2.0303. Min Act: -0.1700

Data Index: 5853901 (Open Web Text)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1308. Min Range: -2.1308

Max Act: 1.9949. Min Act: -0.1700

Data Index: 4135089 (Open Web Text)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #19