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

Dataset: The Pile

Neuron 697 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: 0.5609. Min Range: -0.5609

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1590184 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1218255 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1789323 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4885. Min Act: -0.0000

Data Index: 924537 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1708293 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1247508 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1808181 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4770. Min Act: -0.0000

Data Index: 304343 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.5168. Min Act: 0.0000

Data Index: 1988741 (The Pile)

Max Activating Token Index: 918

Text #9

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4807. Min Act: -0.0000

Data Index: 216734 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1904270 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4725. Min Act: 0.0000

Data Index: 1534787 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1130628 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1843663 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4560. Min Act: 0.0000

Data Index: 937282 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4846. Min Act: -0.0000

Data Index: 946060 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1479904 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1339994 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4780. Min Act: -0.0000

Data Index: 551637 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4464. Min Act: -0.0000

Data Index: 808160 (The Pile)

Max Activating Token Index: 813