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

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

Neuron 1825 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: 0.0355. Min Range: -0.0355

Max Act: 0.0348. Min Act: -0.0003

Data Index: 429021 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0343. Min Act: -0.0004

Data Index: 262016 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0344. Min Act: -0.0003

Data Index: 722365 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0345. Min Act: -0.0003

Data Index: 113303 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0003

Data Index: 583399 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0336. Min Act: -0.0003

Data Index: 478462 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0337. Min Act: -0.0003

Data Index: 787090 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0335. Min Act: -0.0003

Data Index: 581281 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0329. Min Act: -0.0003

Data Index: 15170 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1170465 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1192422 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1024495 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0333. Min Act: -0.0003

Data Index: 200274 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1063954 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0004

Data Index: 333697 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0351. Min Act: -0.0003

Data Index: 675166 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0337. Min Act: -0.0003

Data Index: 921355 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1076692 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0334. Min Act: -0.0003

Data Index: 160779 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0329. Min Act: -0.0003

Data Index: 791495 (C4 (Web Text))

Max Activating Token Index: 368