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

Dataset: The Pile

Neuron 1023 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0897. Min Range: -8.0897

Max Act: 8.0897. Min Act: -0.0000

Data Index: 1844959 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.7190. Min Act: -0.0000

Data Index: 1813670 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.6208. Min Act: -0.0000

Data Index: 1821430 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.3907. Min Act: -0.0000

Data Index: 1625544 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.5989. Min Act: -0.0000

Data Index: 1510655 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.7779. Min Act: -0.0000

Data Index: 1405056 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.4517. Min Act: -0.0000

Data Index: 1106999 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.1032. Min Act: -0.0000

Data Index: 644916 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.2694. Min Act: -0.0000

Data Index: 813729 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 8.0897. Min Range: -8.0897

Max Act: 6.7456. Min Act: -0.0000

Data Index: 285477 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 8.0897. Min Range: -8.0897

Max Act: 7.2229. Min Act: -0.0000

Data Index: 150599 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 8.0897. Min Range: -8.0897

Max Act: 6.6442. Min Act: -0.0000

Data Index: 1207889 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 8.0897. Min Range: -8.0897

Max Act: 6.3015. Min Act: -0.0000

Data Index: 327380 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 8.0897. Min Range: -8.0897

Max Act: 6.3472. Min Act: -0.0000

Data Index: 1586648 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 8.0897. Min Range: -8.0897

Max Act: 5.7840. Min Act: -0.0000

Data Index: 1517171 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 8.0897. Min Range: -8.0897

Max Act: 6.0891. Min Act: -0.0000

Data Index: 1055989 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 8.0897. Min Range: -8.0897

Max Act: 6.1485. Min Act: -0.0000

Data Index: 1954263 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 8.0897. Min Range: -8.0897

Max Act: 5.8133. Min Act: -0.0000

Data Index: 854593 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 8.0897. Min Range: -8.0897

Max Act: 5.2517. Min Act: -0.0000

Data Index: 1003371 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 8.0897. Min Range: -8.0897

Max Act: 5.8084. Min Act: -0.0000

Data Index: 1663868 (The Pile)

Max Activating Token Index: 850