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

Dataset: Open Web Text

Neuron 2042 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: 3.2543. Min Range: -3.2543

Max Act: 3.2543. Min Act: -0.1700

Data Index: 485225 (Open Web Text)

Max Activating Token Index: 173

Text #1

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.2277. Min Act: -0.1700

Data Index: 107789 (Open Web Text)

Max Activating Token Index: 294

Text #2

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.2537. Min Act: -0.1700

Data Index: 4372810 (Open Web Text)

Max Activating Token Index: 826

Text #3

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1835. Min Act: -0.1700

Data Index: 8124039 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1928. Min Act: -0.1700

Data Index: 4693543 (Open Web Text)

Max Activating Token Index: 256

Text #5

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1642. Min Act: -0.1700

Data Index: 5952511 (Open Web Text)

Max Activating Token Index: 54

Text #6

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1309. Min Act: -0.1700

Data Index: 3106278 (Open Web Text)

Max Activating Token Index: 652

Text #7

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1548. Min Act: -0.1700

Data Index: 137957 (Open Web Text)

Max Activating Token Index: 701

Text #8

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1445. Min Act: -0.1700

Data Index: 344824 (Open Web Text)

Max Activating Token Index: 406

Text #9

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1379. Min Act: -0.1700

Data Index: 8712335 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1420. Min Act: -0.1700

Data Index: 6770637 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1302. Min Act: -0.1700

Data Index: 3877427 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1167. Min Act: -0.1700

Data Index: 7066543 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1188. Min Act: -0.1700

Data Index: 4348061 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1190. Min Act: -0.1700

Data Index: 2915812 (Open Web Text)

Max Activating Token Index: 279

Text #15

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1259. Min Act: -0.1700

Data Index: 1551671 (Open Web Text)

Max Activating Token Index: 729

Text #16

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1204. Min Act: -0.1700

Data Index: 2136051 (Open Web Text)

Max Activating Token Index: 395

Text #17

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1288. Min Act: -0.1700

Data Index: 2269017 (Open Web Text)

Max Activating Token Index: 564

Text #18

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.1235. Min Act: -0.1700

Data Index: 86516 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 3.2543. Min Range: -3.2543

Max Act: 3.0889. Min Act: -0.1700

Data Index: 2998388 (Open Web Text)

Max Activating Token Index: 264