Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4879 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.9167. Min Act: -0.0001

Data Index: 685362 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7932. Min Act: -0.0001

Data Index: 270513 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1620355 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7411. Min Act: -0.0001

Data Index: 198406 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7384. Min Act: -0.0000

Data Index: 170822 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7902. Min Act: -0.0001

Data Index: 599608 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7652. Min Act: -0.0001

Data Index: 1332888 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7165. Min Act: -0.0001

Data Index: 850107 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7245. Min Act: -0.0001

Data Index: 1509008 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7254. Min Act: -0.0001

Data Index: 801504 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7497. Min Act: -0.0001

Data Index: 1337481 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6980. Min Act: -0.0001

Data Index: 426524 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7030. Min Act: -0.0001

Data Index: 472540 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6434. Min Act: -0.0001

Data Index: 441683 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7193. Min Act: -0.0001

Data Index: 134223 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6814. Min Act: -0.0000

Data Index: 427395 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6969. Min Act: -0.0000

Data Index: 302980 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6267. Min Act: -0.0001

Data Index: 584996 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6701. Min Act: -0.0001

Data Index: 422562 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6265. Min Act: -0.0001

Data Index: 601093 (C4 (Web Text))

Max Activating Token Index: 18