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

Dataset: The Pile

Neuron 4423 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6594. Min Act: -0.0000

Data Index: 241258 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1291592 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4244. Min Act: -0.0000

Data Index: 931605 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1039735 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1491170 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1103160 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1176382 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4090. Min Act: -0.0000

Data Index: 645026 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1184206 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3953. Min Act: -0.0000

Data Index: 143703 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1845607 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1793825 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1212281 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3683. Min Act: -0.0000

Data Index: 544512 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1150905 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1025179 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3386. Min Act: -0.0000

Data Index: 493599 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3565. Min Act: -0.0000

Data Index: 96491 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3188. Min Act: -0.0000

Data Index: 843958 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3326. Min Act: -0.0000

Data Index: 553422 (The Pile)

Max Activating Token Index: 438