Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1382. Min Act: -0.0002

Data Index: 967168 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1305554 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1472. Min Act: -0.0002

Data Index: 1110099 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1175891 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1355. Min Act: -0.0002

Data Index: 855520 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1180. Min Act: -0.0002

Data Index: 67210 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1069825 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1180. Min Act: -0.0002

Data Index: 26389 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1171. Min Act: -0.0002

Data Index: 180040 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1135. Min Act: -0.0002

Data Index: 526586 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1279. Min Act: -0.0002

Data Index: 956375 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1255. Min Act: -0.0002

Data Index: 1352957 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1313. Min Act: -0.0002

Data Index: 330423 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1355. Min Act: -0.0002

Data Index: 476135 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1076517 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1256. Min Act: -0.0002

Data Index: 38384 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1197414 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1198. Min Act: -0.0002

Data Index: 685307 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1256. Min Act: -0.0002

Data Index: 102200 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1209. Min Act: -0.0002

Data Index: 608687 (C4 (Web Text))

Max Activating Token Index: 1006