Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 400 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.1941. Min Act: -0.0002

Data Index: 562051 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.1222. Min Act: -0.0002

Data Index: 797246 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.1229. Min Act: -0.0002

Data Index: 87282 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.0934. Min Act: -0.0002

Data Index: 495226 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.0799. Min Act: -0.0002

Data Index: 803185 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9657. Min Act: -0.0002

Data Index: 1229923 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9894. Min Act: -0.0002

Data Index: 151343 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.0804. Min Act: -0.0002

Data Index: 1169103 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8636. Min Act: -0.0002

Data Index: 604379 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9262. Min Act: -0.0002

Data Index: 1094835 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9790. Min Act: -0.0002

Data Index: 1237915 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9419. Min Act: -0.0002

Data Index: 619992 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8577. Min Act: -0.0002

Data Index: 1232490 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8542. Min Act: -0.0002

Data Index: 401449 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8571. Min Act: -0.0002

Data Index: 335020 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8544. Min Act: -0.0002

Data Index: 1186810 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9143. Min Act: -0.0002

Data Index: 191897 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8829. Min Act: -0.0002

Data Index: 1071849 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.7944. Min Act: -0.0002

Data Index: 660153 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8447. Min Act: -0.0002

Data Index: 225499 (C4 (Web Text))

Max Activating Token Index: 108