< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 475 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.6526. Min Act: -0.1700

Data Index: 3246553 (Open Web Text)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.6262. Min Act: -0.1700

Data Index: 3629547 (Open Web Text)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.5871. Min Act: -0.1700

Data Index: 1333393 (Open Web Text)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.5679. Min Act: -0.1700

Data Index: 4738592 (Open Web Text)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.4983. Min Act: -0.1700

Data Index: 8383700 (Open Web Text)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3642. Min Act: -0.1700

Data Index: 6471879 (Open Web Text)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3698. Min Act: -0.1700

Data Index: 506950 (Open Web Text)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3585. Min Act: -0.1700

Data Index: 6275513 (Open Web Text)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3797. Min Act: -0.1700

Data Index: 8214849 (Open Web Text)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3791. Min Act: -0.1700

Data Index: 13520 (Open Web Text)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3912. Min Act: -0.1700

Data Index: 5434244 (Open Web Text)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3362. Min Act: -0.1700

Data Index: 6654072 (Open Web Text)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3395. Min Act: -0.1700

Data Index: 1852003 (Open Web Text)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3593. Min Act: -0.1700

Data Index: 934018 (Open Web Text)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3395. Min Act: -0.1700

Data Index: 4066576 (Open Web Text)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3419. Min Act: -0.1700

Data Index: 7671483 (Open Web Text)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3319. Min Act: -0.1700

Data Index: 3422136 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3129. Min Act: -0.1700

Data Index: 397588 (Open Web Text)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3325. Min Act: -0.1700

Data Index: 2518929 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.6526. Min Range: -4.6526

Max Act: 4.3173. Min Act: -0.1700

Data Index: 470642 (Open Web Text)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #19