Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 448 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1020188 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1356. Min Act: -0.0001

Data Index: 439721 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1258. Min Act: -0.0001

Data Index: 161577 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1023598 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1343649 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1326. Min Act: -0.0001

Data Index: 641404 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1105478 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1248. Min Act: -0.0001

Data Index: 654699 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1283. Min Act: -0.0001

Data Index: 916334 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1339442 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1165. Min Act: -0.0001

Data Index: 565603 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1187. Min Act: -0.0001

Data Index: 146317 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1374. Min Act: -0.0001

Data Index: 323650 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1192. Min Act: -0.0001

Data Index: 642897 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1075. Min Act: -0.0001

Data Index: 692354 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1380. Min Act: -0.0001

Data Index: 440842 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1085. Min Act: -0.0001

Data Index: 903287 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1195. Min Act: -0.0001

Data Index: 396776 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1188. Min Act: -0.0001

Data Index: 614749 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1180. Min Act: -0.0001

Data Index: 644647 (C4 (Web Text))

Max Activating Token Index: 921