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

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

Neuron 3351 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7913. Min Act: -0.0002

Data Index: 132409 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7681. Min Act: -0.0002

Data Index: 942002 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7818. Min Act: -0.0002

Data Index: 630661 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7384. Min Act: -0.0002

Data Index: 1137326 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7502. Min Act: -0.0002

Data Index: 351874 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7311. Min Act: -0.0002

Data Index: 1249974 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7301. Min Act: -0.0002

Data Index: 918843 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7290. Min Act: -0.0002

Data Index: 709603 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7204. Min Act: -0.0002

Data Index: 222916 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7195. Min Act: -0.0003

Data Index: 711894 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7153. Min Act: -0.0002

Data Index: 265182 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7058. Min Act: -0.0002

Data Index: 109433 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7139. Min Act: -0.0002

Data Index: 577299 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7086. Min Act: -0.0002

Data Index: 1095988 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7053. Min Act: -0.0002

Data Index: 459748 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7083. Min Act: -0.0002

Data Index: 529156 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7226. Min Act: -0.0002

Data Index: 427371 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7116. Min Act: -0.0002

Data Index: 1053721 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7113. Min Act: -0.0002

Data Index: 754668 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6987. Min Act: -0.0003

Data Index: 36762 (C4 (Web Text))

Max Activating Token Index: 418