Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 783 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.7476. Min Act: -0.0000

Data Index: 110846 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.7565. Min Act: -0.0000

Data Index: 138495 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6974. Min Act: -0.0000

Data Index: 46013 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1971754 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6461. Min Act: -0.0000

Data Index: 212671 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1152021 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6802. Min Act: -0.0000

Data Index: 787552 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1717200 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6960. Min Act: -0.0000

Data Index: 108799 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6945. Min Act: -0.0000

Data Index: 394336 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1025129 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1255425 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1536878 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1431864 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6577. Min Act: -0.0000

Data Index: 271190 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.5943. Min Act: -0.0000

Data Index: 326251 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.5841. Min Act: -0.0000

Data Index: 444718 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.5527. Min Act: -0.0000

Data Index: 149417 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1306445 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.5460. Min Act: -0.0000

Data Index: 439918 (The Pile)

Max Activating Token Index: 103