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

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

Neuron 3702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.6284. Min Act: -0.0000

Data Index: 936334 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.7446. Min Act: -0.0000

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1248889 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0198. Min Act: -0.0000

Data Index: 346908 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1147296 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1105871 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0146. Min Act: -0.0000

Data Index: 273768 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0173. Min Act: -0.0000

Data Index: 873915 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0187. Min Act: -0.0000

Data Index: 1244067 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0176. Min Act: -0.0000

Data Index: 1204265 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0152. Min Act: -0.0000

Data Index: 605938 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0160. Min Act: -0.0001

Data Index: 297099 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0170. Min Act: -0.0001

Data Index: 24631 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1200180 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0173. Min Act: -0.0000

Data Index: 884321 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0173. Min Act: -0.0000

Data Index: 142816 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0159. Min Act: -0.0001

Data Index: 436669 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0166. Min Act: -0.0001

Data Index: 478523 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0153. Min Act: -0.0001

Data Index: 1172413 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.7446. Min Range: -0.7446

Max Act: 0.0192. Min Act: -0.0001

Data Index: 108188 (C4 (Web Text))

Max Activating Token Index: 807