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

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

Neuron 3147 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0002

Data Index: 211013 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0322. Min Act: -0.0003

Data Index: 400912 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0333. Min Act: -0.0002

Data Index: 348925 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0288. Min Act: -0.0003

Data Index: 624925 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0280. Min Act: -0.0003

Data Index: 648626 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1128204 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1102935 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0268. Min Act: -0.0003

Data Index: 744925 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0260. Min Act: -0.0002

Data Index: 894362 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0255. Min Act: -0.0003

Data Index: 888262 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0264. Min Act: -0.0003

Data Index: 976681 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0252. Min Act: -0.0003

Data Index: 595937 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1307265 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0255. Min Act: -0.0002

Data Index: 529682 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0259. Min Act: -0.0003

Data Index: 778150 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0240. Min Act: -0.0003

Data Index: 508834 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0248. Min Act: -0.0003

Data Index: 644428 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0250. Min Act: -0.0003

Data Index: 436787 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0260. Min Act: -0.0003

Data Index: 528226 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0260. Min Act: -0.0002

Data Index: 336913 (C4 (Web Text))

Max Activating Token Index: 294