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

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

Neuron 2230 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0003

Data Index: 557174 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0311. Min Act: -0.0003

Data Index: 646989 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1047555 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1454606 (Python Code)

Max Activating Token Index: 269

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1411686 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0304. Min Act: -0.0003

Data Index: 590813 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1217380 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0272. Min Act: -0.0003

Data Index: 820507 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0279. Min Act: -0.0004

Data Index: 152940 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1275204 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1535681 (Python Code)

Max Activating Token Index: 960

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0271. Min Act: -0.0003

Data Index: 672404 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1022262 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0265. Min Act: -0.0003

Data Index: 77560 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1339730 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0254. Min Act: -0.0003

Data Index: 513512 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0265. Min Act: -0.0004

Data Index: 1608804 (Python Code)

Max Activating Token Index: 165

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0263. Min Act: -0.0003

Data Index: 36591 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0274. Min Act: -0.0003

Data Index: 499906 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1360289 (Python Code)

Max Activating Token Index: 805