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

Dataset: The Pile

Neuron 2280 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1923613 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.8476. Min Act: -0.0000

Data Index: 310782 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.7642. Min Act: -0.0000

Data Index: 468075 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1466955 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6587. Min Act: -0.0000

Data Index: 298188 (The Pile)

Max Activating Token Index: 819

Text #5

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1476630 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5685. Min Act: -0.0000

Data Index: 213973 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1262944 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1850298 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1869350 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1792348 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1086412 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1788305 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1889573 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5482. Min Act: -0.0000

Data Index: 93612 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5463. Min Act: -0.0000

Data Index: 599952 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1914802 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1773028 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1866016 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 0.8959. Min Range: -0.8959

Max Act: 0.5440. Min Act: -0.0000

Data Index: 780627 (The Pile)

Max Activating Token Index: 336