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

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

Neuron 1956 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: 1.8872. Min Range: -1.8872

Max Act: 1.8872. Min Act: -0.0000

Data Index: 1293567 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.8560. Min Act: -0.0000

Data Index: 18483 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1347804 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.5608. Min Act: -0.0000

Data Index: 349017 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1158401 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.4442. Min Act: -0.0000

Data Index: 37543 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.4363. Min Act: -0.0000

Data Index: 588615 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.3397. Min Act: -0.0000

Data Index: 851640 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.3893. Min Act: -0.0000

Data Index: 867823 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.2585. Min Act: -0.0000

Data Index: 902755 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.2240. Min Act: -0.0000

Data Index: 929733 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.1468. Min Act: 0.0000

Data Index: 614701 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.2117. Min Act: -0.0000

Data Index: 822029 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.2031. Min Act: -0.0000

Data Index: 235258 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.1354. Min Act: -0.0000

Data Index: 458895 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.2723. Min Act: 0.0000

Data Index: 529887 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.1964. Min Act: -0.0000

Data Index: 584858 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.2452. Min Act: -0.0000

Data Index: 421114 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.1902. Min Act: 0.0000

Data Index: 1086463 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.8872. Min Range: -1.8872

Max Act: 1.1726. Min Act: -0.0000

Data Index: 845197 (C4 (Web Text))

Max Activating Token Index: 1011