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

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

Neuron 3605 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.8750. Min Act: -0.0000

Data Index: 328294 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.9259. Min Act: -0.0000

Data Index: 397301 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.8968. Min Act: -0.0000

Data Index: 551123 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.9196. Min Act: -0.0000

Data Index: 586258 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1082974 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.8211. Min Act: -0.0000

Data Index: 356223 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.9031. Min Act: -0.0000

Data Index: 183093 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.8138. Min Act: -0.0000

Data Index: 627122 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1129260 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.8037. Min Act: -0.0000

Data Index: 523285 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1079268 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7717. Min Act: -0.0000

Data Index: 821380 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7264. Min Act: -0.0000

Data Index: 263420 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7363. Min Act: -0.0000

Data Index: 335908 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1140885 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7525. Min Act: -0.0000

Data Index: 660543 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.6764. Min Act: -0.0000

Data Index: 694923 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7406. Min Act: -0.0000

Data Index: 158968 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7178. Min Act: -0.0000

Data Index: 109823 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1308939 (C4 (Web Text))

Max Activating Token Index: 431