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

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

Neuron 1095 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: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0002

Data Index: 596804 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0176. Min Act: -0.0002

Data Index: 934848 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0176. Min Act: -0.0002

Data Index: 918411 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0169. Min Act: -0.0002

Data Index: 252837 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0169. Min Act: -0.0002

Data Index: 945537 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0002

Data Index: 168463 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1153762 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1031512 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0162. Min Act: -0.0002

Data Index: 819237 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0162. Min Act: -0.0002

Data Index: 422531 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1350572 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0002

Data Index: 839477 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0002

Data Index: 485825 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0002

Data Index: 899136 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0155. Min Act: -0.0002

Data Index: 636172 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0155. Min Act: -0.0002

Data Index: 889243 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0002

Data Index: 912660 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0002

Data Index: 290564 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0002

Data Index: 525965 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1015019 (C4 (Web Text))

Max Activating Token Index: 125