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

Dataset: The Pile

Neuron 4725 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4728. Min Range: -1.4728

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1395121 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 1.4728. Min Range: -1.4728

Max Act: 1.4728. Min Act: -0.0000

Data Index: 367518 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 1.4728. Min Range: -1.4728

Max Act: 1.0724. Min Act: -0.0000

Data Index: 96793 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8958. Min Act: -0.0000

Data Index: 615768 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.9054. Min Act: -0.0000

Data Index: 82536 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.9506. Min Act: -0.0000

Data Index: 36018 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1128050 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7718. Min Act: 0.0000

Data Index: 658548 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1918608 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1074807 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1299204 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7801. Min Act: -0.0000

Data Index: 905716 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7799. Min Act: 0.0000

Data Index: 1899895 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8234. Min Act: 0.0000

Data Index: 285725 (The Pile)

Max Activating Token Index: 507

Text #14

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1009413 (The Pile)

Max Activating Token Index: 787

Text #15

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7865. Min Act: -0.0000

Data Index: 536314 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1313845 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1536611 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1983433 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.4728. Min Range: -1.4728

Max Act: 0.7362. Min Act: -0.0000

Data Index: 349897 (The Pile)

Max Activating Token Index: 168