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

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

Neuron 1693 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3171. Min Range: -8.3171

Max Act: 8.3171. Min Act: -0.0000

Data Index: 1099142 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 8.3171. Min Range: -8.3171

Max Act: 7.8564. Min Act: -0.0000

Data Index: 414112 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 8.3171. Min Range: -8.3171

Max Act: 7.7750. Min Act: -0.0000

Data Index: 1267023 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 8.3171. Min Range: -8.3171

Max Act: 7.8460. Min Act: -0.0000

Data Index: 1238876 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 8.3171. Min Range: -8.3171

Max Act: 7.1123. Min Act: -0.0000

Data Index: 907172 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 8.3171. Min Range: -8.3171

Max Act: 7.0219. Min Act: -0.0000

Data Index: 675453 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 8.3171. Min Range: -8.3171

Max Act: 6.7723. Min Act: -0.0000

Data Index: 702031 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 8.3171. Min Range: -8.3171

Max Act: 5.8292. Min Act: -0.0000

Data Index: 844026 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 8.3171. Min Range: -8.3171

Max Act: 5.5682. Min Act: -0.0000

Data Index: 806896 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.9605. Min Act: -0.0000

Data Index: 743415 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.8345. Min Act: -0.0000

Data Index: 338299 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.7771. Min Act: -0.0000

Data Index: 1092061 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.4831. Min Act: -0.0000

Data Index: 1181384 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.5408. Min Act: -0.0000

Data Index: 707063 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.5629. Min Act: -0.0000

Data Index: 976538 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.9318. Min Act: -0.0000

Data Index: 1138883 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.2260. Min Act: -0.0000

Data Index: 138416 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.3774. Min Act: -0.0000

Data Index: 875385 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.7129. Min Act: -0.0000

Data Index: 1349416 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 8.3171. Min Range: -8.3171

Max Act: 4.4132. Min Act: -0.0000

Data Index: 378197 (C4 (Web Text))

Max Activating Token Index: 295