Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4474 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0244. Min Act: -0.0003

Data Index: 931226 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0212. Min Act: -0.0003

Data Index: 782921 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0208. Min Act: -0.0002

Data Index: 12174 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0191. Min Act: -0.0003

Data Index: 209476 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0172. Min Act: -0.0003

Data Index: 147080 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0174. Min Act: -0.0003

Data Index: 304628 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0160. Min Act: -0.0003

Data Index: 566781 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0159. Min Act: -0.0003

Data Index: 15053 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0156. Min Act: -0.0003

Data Index: 662905 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0154. Min Act: -0.0003

Data Index: 328986 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0157. Min Act: -0.0003

Data Index: 999311 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0157. Min Act: -0.0003

Data Index: 810390 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1292972 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1253601 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0152. Min Act: -0.0003

Data Index: 796564 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0156. Min Act: -0.0002

Data Index: 81054 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1137483 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0149. Min Act: -0.0003

Data Index: 895763 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0153. Min Act: -0.0003

Data Index: 414036 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1064637 (C4 (Web Text))

Max Activating Token Index: 49