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

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

Neuron 1683 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: 0.0042. Min Range: -0.0042

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1391001 (Python Code)

Max Activating Token Index: 609

Text #1

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1300893 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1023385 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0006

Data Index: 480491 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0006

Data Index: 48726 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0005

Data Index: 668151 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0006

Data Index: 371000 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0006

Data Index: 320512 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0005

Data Index: 516341 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0041. Min Act: -0.0006

Data Index: 886364 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0005

Data Index: 370290 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0006

Data Index: 538007 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0006

Data Index: 420 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0005

Data Index: 614988 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0005

Data Index: 150492 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0005

Data Index: 166231 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0039. Min Act: -0.0005

Data Index: 89648 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0039. Min Act: -0.0005

Data Index: 989354 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0040. Min Act: -0.0006

Data Index: 986184 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0042. Min Range: -0.0042

Max Act: 0.0039. Min Act: -0.0005

Data Index: 35885 (C4 (Web Text))

Max Activating Token Index: 954