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

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

Neuron 1131 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0328. Min Act: -0.0004

Data Index: 533229 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0346. Min Act: -0.0004

Data Index: 956040 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0352. Min Act: -0.0004

Data Index: 632269 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1187891 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0334. Min Act: -0.0004

Data Index: 874724 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0335. Min Act: -0.0004

Data Index: 769432 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0335. Min Act: -0.0004

Data Index: 1263875 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1192087 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0333. Min Act: -0.0004

Data Index: 730963 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0326. Min Act: -0.0004

Data Index: 531765 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0325. Min Act: -0.0004

Data Index: 782400 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0004

Data Index: 1150071 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0321. Min Act: -0.0004

Data Index: 1119513 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0308. Min Act: -0.0004

Data Index: 73652 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0322. Min Act: -0.0004

Data Index: 846065 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0343. Min Act: -0.0004

Data Index: 442560 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0305. Min Act: -0.0004

Data Index: 744716 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1179453 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0322. Min Act: -0.0004

Data Index: 880771 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0318. Min Act: -0.0004

Data Index: 984714 (C4 (Web Text))

Max Activating Token Index: 654