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

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

Neuron 1684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.7627. Min Act: -0.0000

Data Index: 878215 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.7573. Min Act: -0.0000

Data Index: 786227 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.7716. Min Act: 0.0000

Data Index: 871049 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.6995. Min Act: 0.0000

Data Index: 599197 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.7104. Min Act: -0.0000

Data Index: 646027 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.6653. Min Act: 0.0000

Data Index: 1262244 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.6750. Min Act: 0.0000

Data Index: 389076 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.5993. Min Act: -0.0000

Data Index: 385922 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.5200. Min Act: -0.0000

Data Index: 522967 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4832. Min Act: -0.0000

Data Index: 189694 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.5156. Min Act: -0.0000

Data Index: 99073 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1250512 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4887. Min Act: -0.0000

Data Index: 265372 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1436024 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4640. Min Act: 0.0000

Data Index: 357371 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4760. Min Act: -0.0000

Data Index: 936558 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1154886 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4695. Min Act: -0.0000

Data Index: 583424 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4502. Min Act: -0.0000

Data Index: 995658 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.7716. Min Range: -0.7716

Max Act: 0.4322. Min Act: 0.0000

Data Index: 319594 (C4 (Web Text))

Max Activating Token Index: 145