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

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

Neuron 1283 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.2321. Min Act: -0.0003

Data Index: 456421 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.1017. Min Act: -0.0003

Data Index: 543480 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.1707. Min Act: -0.0003

Data Index: 487358 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0530. Min Act: -0.0003

Data Index: 656179 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0715. Min Act: -0.0003

Data Index: 108841 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0687. Min Act: -0.0003

Data Index: 1177343 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0653. Min Act: -0.0002

Data Index: 1164486 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9971. Min Act: -0.0003

Data Index: 1205388 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0401. Min Act: -0.0003

Data Index: 178991 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0101. Min Act: -0.0003

Data Index: 1121067 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0080. Min Act: -0.0003

Data Index: 571833 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9978. Min Act: -0.0003

Data Index: 909315 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9937. Min Act: -0.0003

Data Index: 1069587 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9337. Min Act: -0.0003

Data Index: 719252 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9873. Min Act: -0.0003

Data Index: 933392 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9868. Min Act: -0.0003

Data Index: 534862 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9851. Min Act: -0.0003

Data Index: 304304 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9815. Min Act: -0.0003

Data Index: 602963 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0387. Min Act: -0.0003

Data Index: 73536 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9769. Min Act: -0.0003

Data Index: 182528 (C4 (Web Text))

Max Activating Token Index: 73