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

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

Neuron 854 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0805. Min Act: -0.0002

Data Index: 426959 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0728. Min Act: -0.0002

Data Index: 604823 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1043891 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0666. Min Act: -0.0002

Data Index: 836141 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0691. Min Act: -0.0002

Data Index: 236402 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0658. Min Act: -0.0002

Data Index: 90702 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0692. Min Act: -0.0002

Data Index: 855959 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0645. Min Act: -0.0002

Data Index: 279536 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0670. Min Act: -0.0002

Data Index: 270380 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0641. Min Act: -0.0002

Data Index: 268320 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1282957 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1047034 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0661. Min Act: -0.0002

Data Index: 203134 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0661. Min Act: -0.0002

Data Index: 915154 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0661. Min Act: -0.0002

Data Index: 617034 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0653. Min Act: -0.0002

Data Index: 648244 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0636. Min Act: -0.0002

Data Index: 373718 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0617. Min Act: -0.0002

Data Index: 235430 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0655. Min Act: -0.0002

Data Index: 472584 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0628. Min Act: -0.0002

Data Index: 211457 (C4 (Web Text))

Max Activating Token Index: 551