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

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

Neuron 3535 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2345. Min Range: -3.2345

Max Act: 3.2345. Min Act: -0.0000

Data Index: 895339 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 3.2345. Min Range: -3.2345

Max Act: 2.8707. Min Act: -0.0001

Data Index: 492099 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 3.2345. Min Range: -3.2345

Max Act: 2.3537. Min Act: -0.0000

Data Index: 373003 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 3.2345. Min Range: -3.2345

Max Act: 2.1350. Min Act: -0.0000

Data Index: 432601 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 3.2345. Min Range: -3.2345

Max Act: 2.0893. Min Act: -0.0000

Data Index: 1115623 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.8512. Min Act: -0.0000

Data Index: 163589 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 3.2345. Min Range: -3.2345

Max Act: 2.0366. Min Act: -0.0001

Data Index: 1233577 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.6503. Min Act: -0.0000

Data Index: 864739 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.8014. Min Act: -0.0001

Data Index: 1346810 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.8907. Min Act: -0.0000

Data Index: 1192828 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.9516. Min Act: -0.0000

Data Index: 372720 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.9604. Min Act: -0.0001

Data Index: 210347 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.9647. Min Act: -0.0000

Data Index: 666297 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.7444. Min Act: -0.0000

Data Index: 96033 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.7180. Min Act: -0.0000

Data Index: 300031 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.8972. Min Act: -0.0000

Data Index: 1097566 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.9887. Min Act: -0.0000

Data Index: 909432 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.7728. Min Act: -0.0000

Data Index: 515526 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.9504. Min Act: -0.0000

Data Index: 489783 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 3.2345. Min Range: -3.2345

Max Act: 1.5834. Min Act: -0.0001

Data Index: 376223 (C4 (Web Text))

Max Activating Token Index: 772