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

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

Neuron 494 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: 0.4875. Min Range: -0.4875

Max Act: 0.4875. Min Act: -0.0000

Data Index: 570411 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4440. Min Act: 0.0002

Data Index: 199975 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4386. Min Act: 0.0000

Data Index: 357239 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4286. Min Act: 0.0001

Data Index: 847668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4295. Min Act: 0.0001

Data Index: 458778 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4268. Min Act: 0.0000

Data Index: 512200 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1066971 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1193162 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4108. Min Act: 0.0000

Data Index: 114032 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4067. Min Act: 0.0000

Data Index: 880022 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3966. Min Act: -0.0000

Data Index: 179284 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3982. Min Act: 0.0001

Data Index: 413611 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3975. Min Act: 0.0000

Data Index: 297384 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3851. Min Act: 0.0000

Data Index: 70988 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3585. Min Act: -0.0000

Data Index: 202338 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3812. Min Act: 0.0001

Data Index: 1212182 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3792. Min Act: 0.0001

Data Index: 1132337 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3494. Min Act: 0.0000

Data Index: 1282122 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3743. Min Act: -0.0000

Data Index: 949209 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3851. Min Act: -0.0000

Data Index: 603614 (C4 (Web Text))

Max Activating Token Index: 533