Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 81 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0004

Data Index: 111685 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0160. Min Act: -0.0003

Data Index: 107326 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0159. Min Act: -0.0004

Data Index: 809167 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0155. Min Act: -0.0004

Data Index: 1127736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0153. Min Act: -0.0004

Data Index: 1035777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0152. Min Act: -0.0003

Data Index: 444476 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0151. Min Act: -0.0003

Data Index: 964483 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0150. Min Act: -0.0004

Data Index: 1195824 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1198116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0150. Min Act: -0.0004

Data Index: 285022 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0145. Min Act: -0.0004

Data Index: 822198 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1060980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1298496 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1195978 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0004

Data Index: 415343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0003

Data Index: 985006 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0003

Data Index: 14886 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1038275 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0147. Min Act: -0.0004

Data Index: 222572 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0147. Min Act: -0.0004

Data Index: 546888 (C4 (Web Text))

Max Activating Token Index: 1023