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

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

Neuron 3750 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: 2.0807. Min Range: -2.0807

Max Act: 2.0807. Min Act: -0.0000

Data Index: 682883 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.9654. Min Act: -0.0000

Data Index: 706522 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 2.0807. Min Range: -2.0807

Max Act: 2.0156. Min Act: -0.0000

Data Index: 331587 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.7279. Min Act: -0.0000

Data Index: 493371 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.7674. Min Act: -0.0000

Data Index: 789462 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1257927 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.4614. Min Act: -0.0000

Data Index: 925460 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.7228. Min Act: -0.0000

Data Index: 56985 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1291266 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.4897. Min Act: -0.0000

Data Index: 469152 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.5593. Min Act: -0.0000

Data Index: 226984 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.3429. Min Act: -0.0000

Data Index: 869971 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.4029. Min Act: -0.0000

Data Index: 120488 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.3836. Min Act: -0.0000

Data Index: 153136 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.3805. Min Act: -0.0000

Data Index: 606212 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1202426 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.4007. Min Act: -0.0000

Data Index: 849185 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1218352 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.4948. Min Act: -0.0000

Data Index: 102390 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 2.0807. Min Range: -2.0807

Max Act: 1.5113. Min Act: -0.0000

Data Index: 209238 (C4 (Web Text))

Max Activating Token Index: 629