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

Dataset: Open Web Text

Neuron 402 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: 5.2373. Min Range: -5.2373

Max Act: 5.2373. Min Act: -0.1700

Data Index: 5007975 (Open Web Text)

Max Activating Token Index: 137

Text #1

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.1621. Min Act: -0.1700

Data Index: 8261103 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.1308. Min Act: -0.1700

Data Index: 8380676 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.0080. Min Act: -0.1700

Data Index: 5874903 (Open Web Text)

Max Activating Token Index: 767

Text #4

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9077. Min Act: -0.1700

Data Index: 2444615 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9302. Min Act: -0.1700

Data Index: 36311 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9211. Min Act: -0.1700

Data Index: 252875 (Open Web Text)

Max Activating Token Index: 942

Text #7

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8500. Min Act: -0.1700

Data Index: 7322177 (Open Web Text)

Max Activating Token Index: 462

Text #8

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8852. Min Act: -0.1700

Data Index: 7564426 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8754. Min Act: -0.1700

Data Index: 1283340 (Open Web Text)

Max Activating Token Index: 339

Text #10

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8398. Min Act: -0.1700

Data Index: 2321630 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8065. Min Act: -0.1700

Data Index: 5348789 (Open Web Text)

Max Activating Token Index: 875

Text #12

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8190. Min Act: -0.1700

Data Index: 696372 (Open Web Text)

Max Activating Token Index: 905

Text #13

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8122. Min Act: -0.1700

Data Index: 1091822 (Open Web Text)

Max Activating Token Index: 148

Text #14

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8267. Min Act: -0.1700

Data Index: 8265469 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.7870. Min Act: -0.1699

Data Index: 3118300 (Open Web Text)

Max Activating Token Index: 349

Text #16

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.8112. Min Act: -0.1700

Data Index: 478100 (Open Web Text)

Max Activating Token Index: 676

Text #17

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.7838. Min Act: -0.1700

Data Index: 4378280 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.7840. Min Act: -0.1700

Data Index: 7341842 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.7601. Min Act: -0.1700

Data Index: 5692109 (Open Web Text)

Max Activating Token Index: 558