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

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

Neuron 2024 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0196. Min Act: -0.0003

Data Index: 811203 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0175. Min Act: -0.0002

Data Index: 800877 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0180. Min Act: -0.0003

Data Index: 332492 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0204. Min Act: -0.0002

Data Index: 841016 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0159. Min Act: -0.0003

Data Index: 278066 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0157. Min Act: -0.0003

Data Index: 148798 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0158. Min Act: -0.0003

Data Index: 83626 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1039667 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1307025 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0148. Min Act: -0.0003

Data Index: 23197 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1271049 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0147. Min Act: -0.0003

Data Index: 862080 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0151. Min Act: -0.0003

Data Index: 186757 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0154. Min Act: -0.0003

Data Index: 132100 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1164429 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0158. Min Act: -0.0002

Data Index: 150551 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1160759 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0155. Min Act: -0.0003

Data Index: 883020 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0155. Min Act: -0.0003

Data Index: 115517 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0149. Min Act: -0.0003

Data Index: 364821 (C4 (Web Text))

Max Activating Token Index: 310