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

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

Neuron 657 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: 1.3455. Min Range: -1.3455

Max Act: 1.3455. Min Act: 0.0002

Data Index: 1019702 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2418. Min Act: -0.0000

Data Index: 1049363 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2261. Min Act: -0.0000

Data Index: 117185 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2207. Min Act: -0.0000

Data Index: 331061 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2561. Min Act: -0.0000

Data Index: 1282816 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1466. Min Act: -0.0000

Data Index: 536403 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1680. Min Act: -0.0000

Data Index: 406255 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1148. Min Act: 0.0002

Data Index: 1231124 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1282. Min Act: -0.0000

Data Index: 992427 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0882. Min Act: -0.0000

Data Index: 474122 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0280. Min Act: -0.0000

Data Index: 985224 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0224. Min Act: -0.0000

Data Index: 346776 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0433. Min Act: -0.0000

Data Index: 48208 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1236655 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0272. Min Act: -0.0000

Data Index: 953100 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0130. Min Act: -0.0000

Data Index: 539978 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1274639 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1032919 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9641. Min Act: -0.0000

Data Index: 989398 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9847. Min Act: -0.0000

Data Index: 222886 (C4 (Web Text))

Max Activating Token Index: 193