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

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

Neuron 2488 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.4474. Min Act: -0.0000

Data Index: 970965 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.4929. Min Act: -0.0000

Data Index: 347824 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1649845 (Python Code)

Max Activating Token Index: 449

Text #3

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.4191. Min Act: -0.0000

Data Index: 833882 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.4267. Min Act: -0.0000

Data Index: 695580 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1253666 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.4068. Min Act: -0.0000

Data Index: 961715 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.4180. Min Act: -0.0000

Data Index: 985399 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3967. Min Act: -0.0000

Data Index: 276188 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.4043. Min Act: -0.0000

Data Index: 45015 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3833. Min Act: -0.0000

Data Index: 142264 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1484058 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1015866 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1639751 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1066192 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3685. Min Act: -0.0000

Data Index: 472482 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3642. Min Act: -0.0000

Data Index: 370179 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1184277 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3530. Min Act: -0.0000

Data Index: 206774 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.4929. Min Range: -0.4929

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1180310 (C4 (Web Text))

Max Activating Token Index: 199