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

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

Neuron 5526 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.6689. Min Act: -0.0000

Data Index: 1210021 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.0620. Min Act: -0.0000

Data Index: 819030 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.0513. Min Act: -0.0000

Data Index: 929685 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.0762. Min Act: -0.0000

Data Index: 465313 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.0345. Min Act: -0.0000

Data Index: 187360 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.9621. Min Act: -0.0000

Data Index: 200578 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.8737. Min Act: -0.0000

Data Index: 789880 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1243615 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.9314. Min Act: -0.0000

Data Index: 453906 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1241541 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1053746 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1125034 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.7552. Min Act: -0.0000

Data Index: 662385 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.7351. Min Act: -0.0000

Data Index: 628378 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.7089. Min Act: -0.0000

Data Index: 965900 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.7016. Min Act: -0.0000

Data Index: 77718 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1224753 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1148466 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1093578 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 1.6689. Min Range: -1.6689

Max Act: 0.6918. Min Act: -0.0000

Data Index: 961729 (C4 (Web Text))

Max Activating Token Index: 899