Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1062 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0045. Min Act: -0.0005

Data Index: 116553 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0044. Min Act: -0.0005

Data Index: 381833 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0043. Min Act: -0.0005

Data Index: 575948 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0043. Min Act: -0.0004

Data Index: 1277678 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0006

Data Index: 474805 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0005

Data Index: 436796 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0043. Min Act: -0.0005

Data Index: 796987 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0005

Data Index: 73215 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0006

Data Index: 669543 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1148074 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0005

Data Index: 529092 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0005

Data Index: 103583 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1062205 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0041. Min Act: -0.0006

Data Index: 649935 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1532370 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0042. Min Act: -0.0005

Data Index: 731855 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0041. Min Act: -0.0005

Data Index: 280547 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0041. Min Act: -0.0005

Data Index: 328569 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0041. Min Act: -0.0005

Data Index: 966744 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1054243 (C4 (Web Text))

Max Activating Token Index: 1008