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

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

Neuron 3878 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0002

Data Index: 156089 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0159. Min Act: -0.0002

Data Index: 914508 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0154. Min Act: -0.0002

Data Index: 612373 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1206013 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0149. Min Act: -0.0002

Data Index: 324769 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1111341 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1161063 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0002

Data Index: 239384 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0145. Min Act: -0.0002

Data Index: 732532 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0145. Min Act: -0.0002

Data Index: 107287 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0144. Min Act: -0.0002

Data Index: 611244 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0143. Min Act: -0.0002

Data Index: 678444 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1289725 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0143. Min Act: -0.0002

Data Index: 43089 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0002

Data Index: 372952 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0140. Min Act: -0.0002

Data Index: 609270 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0140. Min Act: -0.0002

Data Index: 858665 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0143. Min Act: -0.0002

Data Index: 79010 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0140. Min Act: -0.0002

Data Index: 665787 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0142. Min Act: -0.0002

Data Index: 347038 (C4 (Web Text))

Max Activating Token Index: 288