Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2995 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0002

Data Index: 198078 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0002

Data Index: 137943 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1026639 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1547074 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0155. Min Act: -0.0002

Data Index: 681399 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0158. Min Act: -0.0002

Data Index: 870974 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0154. Min Act: -0.0002

Data Index: 906259 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0155. Min Act: -0.0002

Data Index: 709865 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0147. Min Act: -0.0002

Data Index: 257950 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0146. Min Act: -0.0002

Data Index: 107237 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0149. Min Act: -0.0002

Data Index: 794858 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0146. Min Act: -0.0002

Data Index: 685529 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0142. Min Act: -0.0002

Data Index: 326211 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0148. Min Act: -0.0002

Data Index: 447932 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0151. Min Act: -0.0002

Data Index: 329619 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0146. Min Act: -0.0002

Data Index: 879281 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0140. Min Act: -0.0002

Data Index: 238255 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1027763 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0138. Min Act: -0.0002

Data Index: 801580 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1473558 (Python Code)

Max Activating Token Index: 717