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

Dataset: The Pile

Neuron 2303 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6694. Min Range: -4.6694

Max Act: 4.6694. Min Act: -0.0000

Data Index: 550497 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 4.6694. Min Range: -4.6694

Max Act: 4.1233. Min Act: -0.0000

Data Index: 1166195 (The Pile)

Max Activating Token Index: 765

Text #2

Max Range: 4.6694. Min Range: -4.6694

Max Act: 4.1566. Min Act: -0.0000

Data Index: 1232912 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 4.6694. Min Range: -4.6694

Max Act: 4.2814. Min Act: -0.0000

Data Index: 415651 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 4.6694. Min Range: -4.6694

Max Act: 4.3117. Min Act: -0.0000

Data Index: 334932 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.9822. Min Act: -0.0000

Data Index: 802371 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 4.6694. Min Range: -4.6694

Max Act: 4.0332. Min Act: -0.0000

Data Index: 1641912 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 4.6694. Min Range: -4.6694

Max Act: 4.0203. Min Act: -0.0000

Data Index: 95657 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.7716. Min Act: -0.0000

Data Index: 1758776 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.8842. Min Act: -0.0000

Data Index: 417035 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.9998. Min Act: -0.0000

Data Index: 327994 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.6816. Min Act: -0.0000

Data Index: 546940 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.7864. Min Act: -0.0000

Data Index: 636223 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.7766. Min Act: -0.0000

Data Index: 1037099 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.5691. Min Act: -0.0000

Data Index: 1517034 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.7075. Min Act: -0.0000

Data Index: 1773364 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.7044. Min Act: -0.0000

Data Index: 1264210 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.3834. Min Act: -0.0000

Data Index: 1309034 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.5372. Min Act: -0.0000

Data Index: 960296 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 4.6694. Min Range: -4.6694

Max Act: 3.6841. Min Act: -0.0000

Data Index: 413866 (The Pile)

Max Activating Token Index: 586