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

Dataset: The Pile

Neuron 2941 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.7407. Min Act: -0.0000

Data Index: 1121480 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1465154 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1435836 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3199. Min Act: -0.0000

Data Index: 417639 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3198. Min Act: 0.0000

Data Index: 1743021 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0883. Min Act: -0.0000

Data Index: 310067 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1893619 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1172. Min Act: -0.0000

Data Index: 580342 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1431. Min Act: 0.0000

Data Index: 1590288 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9737. Min Act: -0.0000

Data Index: 993076 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0333. Min Act: -0.0000

Data Index: 480927 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1309819 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1280. Min Act: -0.0000

Data Index: 864583 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0891. Min Act: -0.0000

Data Index: 880546 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9894. Min Act: -0.0000

Data Index: 363224 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1037142 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0003. Min Act: -0.0000

Data Index: 386050 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1615. Min Act: 0.0001

Data Index: 79594 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9747. Min Act: -0.0000

Data Index: 574987 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1068560 (The Pile)

Max Activating Token Index: 48