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

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

Neuron 4613 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.2122. Min Act: -0.0000

Data Index: 550215 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.9689. Min Act: -0.0000

Data Index: 231017 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.1056. Min Act: -0.0000

Data Index: 955979 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.7780. Min Act: -0.0000

Data Index: 184974 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.4728. Min Act: -0.0000

Data Index: 615215 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.5986. Min Act: -0.0000

Data Index: 677196 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.4090. Min Act: -0.0000

Data Index: 1199484 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.5302. Min Act: -0.0000

Data Index: 496052 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.2481. Min Act: -0.0000

Data Index: 1577033 (Python Code)

Max Activating Token Index: 298

Text #9

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.3429. Min Act: -0.0000

Data Index: 1518064 (Python Code)

Max Activating Token Index: 509

Text #10

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.3445. Min Act: -0.0000

Data Index: 1389881 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.3438. Min Act: -0.0000

Data Index: 433168 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.3267. Min Act: -0.0000

Data Index: 858564 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.1524. Min Act: -0.0000

Data Index: 1510245 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.4001. Min Act: -0.0000

Data Index: 1509781 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.2550. Min Act: -0.0000

Data Index: 346178 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.2509. Min Act: -0.0000

Data Index: 234469 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.2254. Min Act: -0.0000

Data Index: 284068 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.1087. Min Act: -0.0000

Data Index: 1008876 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.1178. Min Act: -0.0000

Data Index: 1110903 (C4 (Web Text))

Max Activating Token Index: 730