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

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

Neuron 5079 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.8495. Min Act: -0.0001

Data Index: 818187 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 2.0471. Min Range: -2.0471

Max Act: 2.0178. Min Act: -0.0000

Data Index: 1349221 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.7092. Min Act: -0.0000

Data Index: 359920 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.8526. Min Act: -0.0000

Data Index: 355017 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 2.0471. Min Range: -2.0471

Max Act: 2.0471. Min Act: -0.0000

Data Index: 183458 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.7760. Min Act: -0.0000

Data Index: 227274 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.8297. Min Act: -0.0000

Data Index: 611015 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.7707. Min Act: -0.0000

Data Index: 134094 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.6977. Min Act: -0.0000

Data Index: 1237962 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.7071. Min Act: -0.0000

Data Index: 507302 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.7862. Min Act: -0.0000

Data Index: 1184968 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.7032. Min Act: -0.0000

Data Index: 303650 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.8479. Min Act: -0.0000

Data Index: 916700 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.7929. Min Act: -0.0000

Data Index: 1208770 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.5080. Min Act: -0.0000

Data Index: 845500 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.4754. Min Act: -0.0000

Data Index: 753784 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.5705. Min Act: -0.0000

Data Index: 109936 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.6931. Min Act: -0.0000

Data Index: 868651 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.4906. Min Act: -0.0000

Data Index: 424543 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 2.0471. Min Range: -2.0471

Max Act: 1.7815. Min Act: -0.0001

Data Index: 1252218 (C4 (Web Text))

Max Activating Token Index: 93