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

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

Neuron 3989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2858. Min Act: -0.0001

Data Index: 936293 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.3076. Min Act: -0.0000

Data Index: 907216 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.3019. Min Act: -0.0000

Data Index: 203478 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1042574 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2899. Min Act: -0.0001

Data Index: 58270 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2725. Min Act: -0.0001

Data Index: 274785 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1133472 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2612. Min Act: -0.0000

Data Index: 961403 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2670. Min Act: -0.0000

Data Index: 214872 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2759. Min Act: -0.0000

Data Index: 785530 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2566. Min Act: -0.0000

Data Index: 179576 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2624. Min Act: -0.0000

Data Index: 854200 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2643. Min Act: -0.0001

Data Index: 785435 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2439. Min Act: -0.0000

Data Index: 57988 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2580. Min Act: -0.0001

Data Index: 9618 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2319. Min Act: -0.0000

Data Index: 293830 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1126204 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2491. Min Act: -0.0001

Data Index: 1188178 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2470. Min Act: -0.0000

Data Index: 97446 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2252. Min Act: -0.0001

Data Index: 616985 (C4 (Web Text))

Max Activating Token Index: 386