Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1602 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1443. Min Act: -0.0006

Data Index: 478417 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1390. Min Act: -0.0006

Data Index: 1280893 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1331. Min Act: -0.0006

Data Index: 207971 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1321. Min Act: -0.0006

Data Index: 838551 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1277. Min Act: -0.0006

Data Index: 839774 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1349. Min Act: -0.0006

Data Index: 165295 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1198. Min Act: -0.0006

Data Index: 1356682 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1279. Min Act: -0.0006

Data Index: 1344014 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1217. Min Act: -0.0006

Data Index: 664146 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1210. Min Act: -0.0006

Data Index: 76855 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1121. Min Act: -0.0006

Data Index: 708660 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1254. Min Act: -0.0006

Data Index: 510138 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1204. Min Act: -0.0006

Data Index: 301478 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1192. Min Act: -0.0006

Data Index: 269849 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1229. Min Act: -0.0006

Data Index: 691371 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1135. Min Act: -0.0006

Data Index: 779392 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1215. Min Act: -0.0006

Data Index: 786848 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1171. Min Act: -0.0006

Data Index: 124772 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1116. Min Act: -0.0006

Data Index: 401381 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1161. Min Act: -0.0006

Data Index: 793816 (C4 (Web Text))

Max Activating Token Index: 207