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

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

Neuron 3697 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: 0.5973. Min Range: -0.5973

Max Act: 0.5973. Min Act: -0.0000

Data Index: 349205 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5886. Min Act: 0.0000

Data Index: 844475 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1332820 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5244. Min Act: -0.0000

Data Index: 802798 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4943. Min Act: -0.0000

Data Index: 900037 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4868. Min Act: -0.0000

Data Index: 361523 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4966. Min Act: -0.0000

Data Index: 594 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4765. Min Act: -0.0000

Data Index: 952315 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4640. Min Act: 0.0000

Data Index: 451462 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4587. Min Act: 0.0000

Data Index: 472023 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4501. Min Act: -0.0000

Data Index: 650791 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4487. Min Act: -0.0000

Data Index: 638701 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1339488 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4148. Min Act: -0.0000

Data Index: 151967 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4301. Min Act: -0.0000

Data Index: 250983 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4242. Min Act: 0.0000

Data Index: 987921 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4245. Min Act: 0.0001

Data Index: 400631 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4193. Min Act: -0.0000

Data Index: 340667 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4165. Min Act: -0.0000

Data Index: 634647 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1084747 (C4 (Web Text))

Max Activating Token Index: 71