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

Dataset: The Pile

Neuron 4040 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: 1.7303. Min Range: -1.7303

Max Act: 1.5743. Min Act: -0.0000

Data Index: 1136000 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.7303. Min Act: -0.0000

Data Index: 963252 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1539538 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2467. Min Act: -0.0000

Data Index: 121087 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1509652 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2561. Min Act: -0.0000

Data Index: 418488 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.0814. Min Act: -0.0000

Data Index: 916536 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1742118 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1851962 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9662. Min Act: -0.0000

Data Index: 275547 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1158070 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1372516 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1941877 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1731059 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1859621 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9247. Min Act: -0.0000

Data Index: 512961 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9196. Min Act: -0.0000

Data Index: 685432 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9269. Min Act: -0.0000

Data Index: 390206 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1807573 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 1.7303. Min Range: -1.7303

Max Act: 0.9024. Min Act: -0.0000

Data Index: 961432 (The Pile)

Max Activating Token Index: 999