Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 98 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0006

Data Index: 886465 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0165. Min Act: -0.0005

Data Index: 1357011 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0164. Min Act: -0.0005

Data Index: 238623 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0163. Min Act: -0.0005

Data Index: 1016955 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0159. Min Act: -0.0005

Data Index: 659921 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0159. Min Act: -0.0005

Data Index: 488257 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0005

Data Index: 460789 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0005

Data Index: 225018 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0005

Data Index: 469309 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0159. Min Act: -0.0005

Data Index: 735237 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0159. Min Act: -0.0005

Data Index: 1004952 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1118215 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0158. Min Act: -0.0005

Data Index: 849221 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0158. Min Act: -0.0005

Data Index: 201111 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0005

Data Index: 1249235 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0006

Data Index: 252128 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0005

Data Index: 747072 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0006

Data Index: 630956 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0005

Data Index: 91185 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0005

Data Index: 309522 (C4 (Web Text))

Max Activating Token Index: 695