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

Dataset: The Pile

Neuron 4901 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.4228. Min Act: -0.0000

Data Index: 131278 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.4021. Min Act: -0.0000

Data Index: 525656 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1891475 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1559608 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1255426 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1919984 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1093155 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1317484 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3471. Min Act: -0.0000

Data Index: 94834 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3599. Min Act: -0.0000

Data Index: 909209 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1529955 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1453501 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1078062 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1007274 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1949495 (The Pile)

Max Activating Token Index: 864

Text #15

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3450. Min Act: -0.0000

Data Index: 811630 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3385. Min Act: -0.0000

Data Index: 25701 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1792195 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3289. Min Act: -0.0000

Data Index: 353496 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1927460 (The Pile)

Max Activating Token Index: 627