Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2024 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3138. Min Act: -0.0001

Data Index: 1043708 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1234061 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2259. Min Act: -0.0002

Data Index: 393604 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2130. Min Act: -0.0001

Data Index: 763529 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2292. Min Act: -0.0002

Data Index: 489150 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1960. Min Act: -0.0001

Data Index: 832078 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2174. Min Act: -0.0002

Data Index: 587199 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2076. Min Act: -0.0002

Data Index: 579854 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1986. Min Act: -0.0002

Data Index: 893734 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2074. Min Act: -0.0002

Data Index: 412105 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2037. Min Act: -0.0002

Data Index: 335717 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1228054 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1956. Min Act: -0.0001

Data Index: 973169 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1773. Min Act: -0.0002

Data Index: 706991 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2081. Min Act: -0.0002

Data Index: 1308359 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2118. Min Act: -0.0002

Data Index: 1035195 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1909. Min Act: -0.0001

Data Index: 916257 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1834. Min Act: -0.0001

Data Index: 903235 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1777. Min Act: -0.0002

Data Index: 1018970 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1942. Min Act: -0.0002

Data Index: 14014 (C4 (Web Text))

Max Activating Token Index: 35