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

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

Neuron 5066 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0249. Min Act: -0.0003

Data Index: 761498 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0003

Data Index: 235030 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1004214 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1136797 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0228. Min Act: -0.0002

Data Index: 770823 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0200. Min Act: -0.0002

Data Index: 830920 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1011127 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1174444 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0192. Min Act: -0.0003

Data Index: 400720 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1248853 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0160. Min Act: -0.0002

Data Index: 147137 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1093831 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0140. Min Act: -0.0002

Data Index: 397749 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0152. Min Act: -0.0002

Data Index: 97 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0155. Min Act: -0.0002

Data Index: 958581 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0158. Min Act: -0.0002

Data Index: 60353 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0148. Min Act: -0.0002

Data Index: 910447 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0143. Min Act: -0.0002

Data Index: 206819 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0138. Min Act: -0.0002

Data Index: 735281 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0148. Min Act: -0.0002

Data Index: 214004 (C4 (Web Text))

Max Activating Token Index: 617