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

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

Neuron 4145 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3100. Min Range: -2.3100

Max Act: 2.3100. Min Act: -0.0000

Data Index: 323502 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 2.3100. Min Range: -2.3100

Max Act: 2.2643. Min Act: -0.0000

Data Index: 1176084 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 2.3100. Min Range: -2.3100

Max Act: 2.0972. Min Act: -0.0000

Data Index: 591725 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.8520. Min Act: -0.0000

Data Index: 385208 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.8254. Min Act: -0.0000

Data Index: 829761 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.7349. Min Act: -0.0000

Data Index: 1066147 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.5879. Min Act: -0.0000

Data Index: 258101 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.6699. Min Act: -0.0000

Data Index: 1112422 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.5771. Min Act: -0.0000

Data Index: 1588709 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1447332 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.5279. Min Act: -0.0000

Data Index: 684478 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.5111. Min Act: -0.0000

Data Index: 840701 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.5108. Min Act: -0.0000

Data Index: 123788 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1433011 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.3947. Min Act: -0.0000

Data Index: 165611 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1474085 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.3480. Min Act: -0.0000

Data Index: 353594 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1578185 (Python Code)

Max Activating Token Index: 874

Text #18

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1057934 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 2.3100. Min Range: -2.3100

Max Act: 1.4188. Min Act: -0.0000

Data Index: 780915 (C4 (Web Text))

Max Activating Token Index: 341