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

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

Neuron 2197 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0001

Data Index: 494580 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0749. Min Act: -0.0001

Data Index: 954127 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0652. Min Act: -0.0001

Data Index: 137301 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1314995 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1258671 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0647. Min Act: -0.0001

Data Index: 822385 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1243161 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1106642 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0597. Min Act: -0.0001

Data Index: 38345 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0548. Min Act: -0.0001

Data Index: 940430 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0570. Min Act: -0.0001

Data Index: 989410 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0574. Min Act: -0.0001

Data Index: 843776 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1046347 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1178905 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1056553 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0543. Min Act: -0.0001

Data Index: 67539 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0541. Min Act: -0.0001

Data Index: 680400 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1203491 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1166906 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0535. Min Act: -0.0001

Data Index: 101026 (C4 (Web Text))

Max Activating Token Index: 535