Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5244 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1303. Min Range: -4.1303

Max Act: 4.0570. Min Act: -0.0000

Data Index: 1355055 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 4.1303. Min Range: -4.1303

Max Act: 4.1303. Min Act: -0.0000

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.9735. Min Act: -0.0000

Data Index: 1350678 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.8115. Min Act: -0.0000

Data Index: 696100 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.7695. Min Act: -0.0000

Data Index: 46618 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.8198. Min Act: -0.0000

Data Index: 675955 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.9627. Min Act: -0.0000

Data Index: 1221361 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.7278. Min Act: -0.0000

Data Index: 813054 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 4.1303. Min Range: -4.1303

Max Act: 4.0770. Min Act: -0.0000

Data Index: 536052 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.7035. Min Act: -0.0000

Data Index: 578827 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.6994. Min Act: -0.0000

Data Index: 871764 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.7062. Min Act: -0.0000

Data Index: 1269453 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.7586. Min Act: -0.0000

Data Index: 1300203 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.5871. Min Act: -0.0000

Data Index: 1045723 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.5652. Min Act: -0.0000

Data Index: 861307 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.5507. Min Act: -0.0000

Data Index: 307105 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.5280. Min Act: -0.0000

Data Index: 765727 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.5226. Min Act: -0.0000

Data Index: 1326969 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.5113. Min Act: -0.0000

Data Index: 93046 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 4.1303. Min Range: -4.1303

Max Act: 3.2862. Min Act: -0.0000

Data Index: 601100 (C4 (Web Text))

Max Activating Token Index: 734