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

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

Neuron 4996 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: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0002

Data Index: 221754 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0151. Min Act: -0.0002

Data Index: 509472 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0150. Min Act: -0.0002

Data Index: 949760 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0149. Min Act: -0.0002

Data Index: 175119 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1295433 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0149. Min Act: -0.0002

Data Index: 94416 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0149. Min Act: -0.0002

Data Index: 35314 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0148. Min Act: -0.0002

Data Index: 408872 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0148. Min Act: -0.0002

Data Index: 450295 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0148. Min Act: -0.0002

Data Index: 974549 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0145. Min Act: -0.0002

Data Index: 666084 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0002

Data Index: 29374 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0147. Min Act: -0.0002

Data Index: 715171 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0146. Min Act: -0.0002

Data Index: 340782 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1067850 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1282406 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0146. Min Act: -0.0002

Data Index: 85715 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0146. Min Act: -0.0002

Data Index: 327236 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0146. Min Act: -0.0002

Data Index: 791120 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0146. Min Act: -0.0002

Data Index: 156382 (C4 (Web Text))

Max Activating Token Index: 852