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

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

Neuron 770 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.4644. Min Act: -0.0000

Data Index: 931129 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.3681. Min Act: -0.0000

Data Index: 336401 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1321593 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.3622. Min Act: 0.0000

Data Index: 660717 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.1639. Min Act: -0.0000

Data Index: 104421 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.1657. Min Act: -0.0000

Data Index: 940269 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.0903. Min Act: -0.0000

Data Index: 111633 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.1519. Min Act: -0.0000

Data Index: 186387 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.0890. Min Act: -0.0000

Data Index: 564719 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1205224 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.4644. Min Range: -1.4644

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1092375 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1083650 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9111. Min Act: -0.0000

Data Index: 38651 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1189257 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9213. Min Act: -0.0000

Data Index: 588647 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.8702. Min Act: 0.0000

Data Index: 908033 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9331. Min Act: -0.0000

Data Index: 163387 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1236740 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9167. Min Act: -0.0000

Data Index: 634566 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.4644. Min Range: -1.4644

Max Act: 0.9698. Min Act: -0.0000

Data Index: 201269 (C4 (Web Text))

Max Activating Token Index: 275