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

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

Neuron 4175 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1558139 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1150943 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.4160. Min Act: -0.0000

Data Index: 645595 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.4553. Min Act: -0.0000

Data Index: 1589900 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.3523. Min Act: -0.0000

Data Index: 270084 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2782. Min Act: -0.0000

Data Index: 76399 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.3238. Min Act: -0.0000

Data Index: 452601 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2649. Min Act: -0.0000

Data Index: 206372 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2251. Min Act: -0.0000

Data Index: 1089698 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1980. Min Act: -0.0000

Data Index: 1065470 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2245. Min Act: -0.0000

Data Index: 1291048 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1708. Min Act: -0.0000

Data Index: 1058395 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1673. Min Act: -0.0000

Data Index: 850103 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1361. Min Act: -0.0000

Data Index: 432679 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1096. Min Act: -0.0000

Data Index: 82013 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1123. Min Act: -0.0000

Data Index: 869449 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1436. Min Act: -0.0000

Data Index: 133468 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1343. Min Act: -0.0000

Data Index: 809938 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1982. Min Act: -0.0000

Data Index: 44013 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1120454 (C4 (Web Text))

Max Activating Token Index: 399