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

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

Neuron 1969 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0174. Min Act: -0.0004

Data Index: 698822 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1198277 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0163. Min Act: -0.0003

Data Index: 789165 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0164. Min Act: -0.0004

Data Index: 403499 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0160. Min Act: -0.0003

Data Index: 896460 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1167371 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0158. Min Act: -0.0004

Data Index: 1342011 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0158. Min Act: -0.0004

Data Index: 546847 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0156. Min Act: -0.0004

Data Index: 734600 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0158. Min Act: -0.0004

Data Index: 1097413 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0155. Min Act: -0.0004

Data Index: 1267860 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0155. Min Act: -0.0004

Data Index: 452797 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0154. Min Act: -0.0003

Data Index: 381399 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1083988 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0152. Min Act: -0.0003

Data Index: 546046 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0152. Min Act: -0.0004

Data Index: 845589 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1268183 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0152. Min Act: -0.0003

Data Index: 435366 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0150. Min Act: -0.0004

Data Index: 653558 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0149. Min Act: -0.0004

Data Index: 1000030 (C4 (Web Text))

Max Activating Token Index: 782