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

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

Neuron 1575 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3138. Min Act: -0.0001

Data Index: 753457 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2568. Min Act: -0.0001

Data Index: 967805 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2767. Min Act: -0.0001

Data Index: 595159 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1959. Min Act: -0.0001

Data Index: 367573 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2462. Min Act: -0.0001

Data Index: 327886 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2647. Min Act: -0.0001

Data Index: 654729 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1320537 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2410. Min Act: -0.0001

Data Index: 1300023 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2416. Min Act: -0.0001

Data Index: 258495 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2294. Min Act: -0.0001

Data Index: 299176 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2097. Min Act: -0.0001

Data Index: 378208 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2155. Min Act: -0.0001

Data Index: 695603 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2153. Min Act: -0.0001

Data Index: 267753 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1837. Min Act: -0.0001

Data Index: 537013 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1132493 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2156. Min Act: -0.0001

Data Index: 887695 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.1919. Min Act: -0.0001

Data Index: 331770 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2287. Min Act: -0.0001

Data Index: 1288067 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2054. Min Act: -0.0001

Data Index: 1216188 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1108960 (C4 (Web Text))

Max Activating Token Index: 548