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

Dataset: The Pile

Neuron 588 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: 1.4436. Min Range: -1.4436

Max Act: 1.4436. Min Act: -0.0000

Data Index: 1815268 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1083489 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1811032 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 1.4436. Min Range: -1.4436

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1906280 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.9202. Min Act: -0.0000

Data Index: 180484 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1993976 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1008269 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1009275 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1433343 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1907425 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.7676. Min Act: -0.0000

Data Index: 648789 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.7592. Min Act: -0.0000

Data Index: 559518 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.7106. Min Act: -0.0000

Data Index: 272825 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1800281 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.7565. Min Act: -0.0000

Data Index: 628048 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.7057. Min Act: -0.0000

Data Index: 127864 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.6999. Min Act: -0.0000

Data Index: 518399 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1459349 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.6384. Min Act: -0.0000

Data Index: 362060 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 1.4436. Min Range: -1.4436

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1787387 (The Pile)

Max Activating Token Index: 438