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

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

Neuron 3594 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.9069. Min Act: -0.0002

Data Index: 395914 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.9543. Min Act: -0.0002

Data Index: 552681 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.9158. Min Act: -0.0002

Data Index: 303116 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8554. Min Act: -0.0002

Data Index: 995229 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7409. Min Act: -0.0002

Data Index: 1047991 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8708. Min Act: -0.0002

Data Index: 1805 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.9257. Min Act: -0.0002

Data Index: 116059 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8277. Min Act: -0.0002

Data Index: 1338318 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8411. Min Act: -0.0002

Data Index: 519728 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8092. Min Act: -0.0002

Data Index: 12572 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7537. Min Act: -0.0002

Data Index: 1332811 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7819. Min Act: -0.0002

Data Index: 165553 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8297. Min Act: -0.0002

Data Index: 167643 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8020. Min Act: -0.0002

Data Index: 607933 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8623. Min Act: -0.0002

Data Index: 610454 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7640. Min Act: -0.0002

Data Index: 559874 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8199. Min Act: -0.0002

Data Index: 1097226 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7858. Min Act: -0.0002

Data Index: 117024 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8390. Min Act: -0.0002

Data Index: 671588 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7903. Min Act: -0.0002

Data Index: 188598 (C4 (Web Text))

Max Activating Token Index: 62