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

Dataset: The Pile

Neuron 2339 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1996. Min Range: -1.1996

Max Act: 1.1996. Min Act: -0.0000

Data Index: 1017408 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 1.1996. Min Range: -1.1996

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1559093 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1151762 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9730. Min Act: -0.0000

Data Index: 786780 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1292784 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1611161 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9712. Min Act: -0.0000

Data Index: 567061 (The Pile)

Max Activating Token Index: 1019

Text #7

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1606508 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9143. Min Act: -0.0000

Data Index: 823472 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9558. Min Act: -0.0000

Data Index: 864750 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1010832 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1072495 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1400995 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9394. Min Act: -0.0000

Data Index: 677010 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1721131 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9017. Min Act: -0.0000

Data Index: 580268 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1283837 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9161. Min Act: -0.0000

Data Index: 338336 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9191. Min Act: -0.0000

Data Index: 832530 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1242611 (The Pile)

Max Activating Token Index: 426