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

Dataset: The Pile

Neuron 1148 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.8871. Min Act: 0.0000

Data Index: 154283 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1711122 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1987145 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1351018 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7974. Min Act: -0.0000

Data Index: 544543 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1042278 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7703. Min Act: 0.0000

Data Index: 1879978 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7857. Min Act: 0.0000

Data Index: 206621 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.8183. Min Act: -0.0000

Data Index: 487477 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7835. Min Act: -0.0000

Data Index: 916353 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7441. Min Act: -0.0000

Data Index: 963615 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1703615 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7039. Min Act: -0.0000

Data Index: 399352 (The Pile)

Max Activating Token Index: 326

Text #13

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7108. Min Act: -0.0000

Data Index: 750429 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1639291 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7173. Min Act: -0.0000

Data Index: 992559 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1315211 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1275637 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.6715. Min Act: -0.0000

Data Index: 183105 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 0.8871. Min Range: -0.8871

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1100158 (The Pile)

Max Activating Token Index: 710