Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 125 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1473. Min Act: -0.0000

Data Index: 739170 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1143. Min Act: -0.0000

Data Index: 710552 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1054. Min Act: -0.0000

Data Index: 801597 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0999. Min Act: -0.0001

Data Index: 949749 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1041. Min Act: -0.0000

Data Index: 460604 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1002770 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1029. Min Act: -0.0000

Data Index: 640476 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1280127 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0972. Min Act: -0.0000

Data Index: 993526 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0963. Min Act: -0.0000

Data Index: 561985 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0967. Min Act: -0.0000

Data Index: 128564 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0961. Min Act: -0.0000

Data Index: 954896 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0959. Min Act: -0.0000

Data Index: 654368 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0946. Min Act: -0.0001

Data Index: 700703 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0975. Min Act: -0.0000

Data Index: 116731 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0978. Min Act: -0.0000

Data Index: 77520 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0979. Min Act: -0.0000

Data Index: 300429 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1244820 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1058421 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0964. Min Act: -0.0000

Data Index: 315112 (C4 (Web Text))

Max Activating Token Index: 490