Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 651 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0349. Min Act: -0.0006

Data Index: 952009 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0352. Min Act: -0.0006

Data Index: 1187749 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0337. Min Act: -0.0006

Data Index: 1295326 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0333. Min Act: -0.0006

Data Index: 218197 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0323. Min Act: -0.0006

Data Index: 374780 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0321. Min Act: -0.0006

Data Index: 308038 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0324. Min Act: -0.0006

Data Index: 867400 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1279390 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0319. Min Act: -0.0006

Data Index: 475853 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1347958 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1207912 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0304. Min Act: -0.0006

Data Index: 231001 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0298. Min Act: -0.0006

Data Index: 631612 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1354614 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0286. Min Act: -0.0006

Data Index: 780168 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0303. Min Act: -0.0006

Data Index: 209663 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0296. Min Act: -0.0006

Data Index: 384337 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0294. Min Act: -0.0006

Data Index: 174295 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0306. Min Act: -0.0006

Data Index: 439405 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0305. Min Act: -0.0006

Data Index: 461331 (C4 (Web Text))

Max Activating Token Index: 715