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

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

Neuron 676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5872. Min Act: -0.0002

Data Index: 1170352 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5817. Min Act: -0.0002

Data Index: 365154 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5381. Min Act: -0.0002

Data Index: 132315 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5333. Min Act: -0.0002

Data Index: 969073 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.4991. Min Act: -0.0002

Data Index: 640691 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5174. Min Act: -0.0002

Data Index: 122712 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5537. Min Act: -0.0002

Data Index: 557347 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5176. Min Act: -0.0002

Data Index: 577955 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5176. Min Act: -0.0002

Data Index: 923911 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.4716. Min Act: -0.0002

Data Index: 171026 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5066. Min Act: -0.0002

Data Index: 608914 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5310. Min Act: -0.0002

Data Index: 1346220 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5060. Min Act: -0.0002

Data Index: 1184742 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5200. Min Act: -0.0002

Data Index: 566333 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5056. Min Act: -0.0002

Data Index: 951737 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.4864. Min Act: -0.0002

Data Index: 95129 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5008. Min Act: -0.0002

Data Index: 955376 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5045. Min Act: -0.0002

Data Index: 894894 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5159. Min Act: -0.0002

Data Index: 38405 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.4830. Min Act: -0.0002

Data Index: 1161954 (C4 (Web Text))

Max Activating Token Index: 333