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

Dataset: Open Web Text

Neuron 2402 in Layer 4

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: 3.3237. Min Range: -3.3237

Max Act: 3.3237. Min Act: -0.1700

Data Index: 2723470 (Open Web Text)

Max Activating Token Index: 677

Text #1

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.2483. Min Act: -0.1700

Data Index: 282855 (Open Web Text)

Max Activating Token Index: 590

Text #2

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.2262. Min Act: -0.1700

Data Index: 5567420 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.2515. Min Act: -0.1700

Data Index: 8591170 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.2304. Min Act: -0.1700

Data Index: 511690 (Open Web Text)

Max Activating Token Index: 687

Text #5

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.2443. Min Act: -0.1700

Data Index: 511687 (Open Web Text)

Max Activating Token Index: 938

Text #6

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.2119. Min Act: -0.1700

Data Index: 3394418 (Open Web Text)

Max Activating Token Index: 381

Text #7

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1755. Min Act: -0.1700

Data Index: 5927682 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1818. Min Act: -0.1700

Data Index: 921524 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1426. Min Act: -0.1700

Data Index: 3078825 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1467. Min Act: -0.1700

Data Index: 2892702 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1356. Min Act: -0.1700

Data Index: 2532151 (Open Web Text)

Max Activating Token Index: 906

Text #12

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1124. Min Act: -0.1700

Data Index: 8469586 (Open Web Text)

Max Activating Token Index: 840

Text #13

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1103. Min Act: -0.1700

Data Index: 1764613 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1313. Min Act: -0.1700

Data Index: 2298951 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1223. Min Act: -0.1700

Data Index: 7752737 (Open Web Text)

Max Activating Token Index: 539

Text #16

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1100. Min Act: -0.1700

Data Index: 3771736 (Open Web Text)

Max Activating Token Index: 1010

Text #17

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.0987. Min Act: -0.1700

Data Index: 5128186 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.0992. Min Act: -0.1700

Data Index: 1884801 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.1343. Min Act: -0.1700

Data Index: 6171661 (Open Web Text)

Max Activating Token Index: 21