Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2266 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0271. Min Act: -0.0001

Data Index: 808291 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0250. Min Act: -0.0001

Data Index: 925742 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1351241 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1495453 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1127326 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0256. Min Act: -0.0001

Data Index: 1023130 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0241. Min Act: -0.0001

Data Index: 736807 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1387688 (Python Code)

Max Activating Token Index: 586

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0237. Min Act: -0.0001

Data Index: 46339 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0256. Min Act: -0.0001

Data Index: 1209240 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1346339 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1346129 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1152743 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0214. Min Act: -0.0001

Data Index: 229969 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0001

Data Index: 711726 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1600981 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1067210 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0234. Min Act: -0.0001

Data Index: 171157 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0219. Min Act: -0.0001

Data Index: 268527 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0221. Min Act: -0.0001

Data Index: 510351 (C4 (Web Text))

Max Activating Token Index: 432