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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 582 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.7848. Min Act: -0.0000

Data Index: 949115 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.7759. Min Act: -0.0000

Data Index: 531400 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.6157. Min Act: -0.0000

Data Index: 1080668 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.3588. Min Act: -0.0000

Data Index: 674422 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.4150. Min Act: -0.0000

Data Index: 1138469 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.2783. Min Act: -0.0000

Data Index: 427009 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.4008. Min Act: -0.0000

Data Index: 1059453 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.2457. Min Act: -0.0000

Data Index: 342381 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.3579. Min Act: -0.0000

Data Index: 548292 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.3325. Min Act: -0.0000

Data Index: 1009125 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.0767. Min Act: -0.0000

Data Index: 603074 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.2863. Min Act: -0.0000

Data Index: 932302 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.2670. Min Act: -0.0000

Data Index: 1002765 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.2266. Min Act: -0.0000

Data Index: 947396 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.2265. Min Act: -0.0000

Data Index: 1280556 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.1851. Min Act: -0.0000

Data Index: 329568 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.0600. Min Act: -0.0000

Data Index: 595859 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.1169. Min Act: -0.0000

Data Index: 709068 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.1346. Min Act: -0.0000

Data Index: 650233 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 2.7848. Min Range: -2.7848

Max Act: 2.0102. Min Act: -0.0000

Data Index: 956169 (C4 (Web Text))

Max Activating Token Index: 419