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

Dataset: Open Web Text

Neuron 2634 in Layer 6

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: 3.2236. Min Range: -3.2236

Max Act: 3.2236. Min Act: -0.1700

Data Index: 5802041 (Open Web Text)

Max Activating Token Index: 196

Text #1

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1998. Min Act: -0.1700

Data Index: 3052374 (Open Web Text)

Max Activating Token Index: 856

Text #2

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1991. Min Act: -0.1700

Data Index: 7617987 (Open Web Text)

Max Activating Token Index: 1007

Text #3

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1603. Min Act: -0.1700

Data Index: 163354 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1297. Min Act: -0.1700

Data Index: 4971090 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1443. Min Act: -0.1700

Data Index: 6136376 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1569. Min Act: -0.1700

Data Index: 3162858 (Open Web Text)

Max Activating Token Index: 684

Text #7

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1303. Min Act: -0.1700

Data Index: 1837337 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1373. Min Act: -0.1700

Data Index: 5604375 (Open Web Text)

Max Activating Token Index: 426

Text #9

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1362. Min Act: -0.1700

Data Index: 2255651 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1283. Min Act: -0.1700

Data Index: 3245381 (Open Web Text)

Max Activating Token Index: 491

Text #11

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1132. Min Act: -0.1700

Data Index: 624146 (Open Web Text)

Max Activating Token Index: 140

Text #12

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0961. Min Act: -0.1700

Data Index: 2932087 (Open Web Text)

Max Activating Token Index: 807

Text #13

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1154. Min Act: -0.1700

Data Index: 5891441 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1209. Min Act: -0.1700

Data Index: 117158 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1216. Min Act: -0.1700

Data Index: 838789 (Open Web Text)

Max Activating Token Index: 604

Text #16

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1205. Min Act: -0.1700

Data Index: 3577462 (Open Web Text)

Max Activating Token Index: 960

Text #17

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1072. Min Act: -0.1700

Data Index: 441015 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0824. Min Act: -0.1700

Data Index: 701698 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0986. Min Act: -0.1700

Data Index: 3303545 (Open Web Text)

Max Activating Token Index: 146