Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 522 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0171. Min Act: -0.0006

Data Index: 353041 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1151649 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0164. Min Act: -0.0006

Data Index: 747080 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0171. Min Act: -0.0006

Data Index: 864165 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0157. Min Act: -0.0006

Data Index: 761938 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0161. Min Act: -0.0006

Data Index: 150838 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0157. Min Act: -0.0006

Data Index: 289028 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0159. Min Act: -0.0006

Data Index: 588700 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0163. Min Act: -0.0005

Data Index: 846391 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0159. Min Act: -0.0006

Data Index: 201132 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0163. Min Act: -0.0006

Data Index: 774273 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0159. Min Act: -0.0006

Data Index: 529857 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0162. Min Act: -0.0006

Data Index: 38470 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1079263 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0154. Min Act: -0.0006

Data Index: 770971 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0152. Min Act: -0.0006

Data Index: 315132 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1317650 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0156. Min Act: -0.0006

Data Index: 127911 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0155. Min Act: -0.0006

Data Index: 762975 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0154. Min Act: -0.0005

Data Index: 955698 (C4 (Web Text))

Max Activating Token Index: 29