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

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

Neuron 3536 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.4105. Min Act: -0.0000

Data Index: 525686 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.3679. Min Act: -0.0000

Data Index: 968618 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.3565. Min Act: -0.0000

Data Index: 30190 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.3280. Min Act: 0.0001

Data Index: 606430 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.3192. Min Act: 0.0000

Data Index: 42018 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.3128. Min Act: -0.0000

Data Index: 60078 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2968. Min Act: -0.0000

Data Index: 647340 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.3184. Min Act: -0.0000

Data Index: 505688 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1174322 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1085974 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2924. Min Act: -0.0000

Data Index: 92429 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2779. Min Act: -0.0000

Data Index: 631572 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1195056 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2752. Min Act: -0.0000

Data Index: 290719 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2835. Min Act: -0.0000

Data Index: 697389 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2822. Min Act: 0.0000

Data Index: 287123 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2684. Min Act: 0.0000

Data Index: 513878 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1079672 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2689. Min Act: 0.0000

Data Index: 549285 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.4105. Min Range: -0.4105

Max Act: 0.2672. Min Act: -0.0000

Data Index: 607252 (C4 (Web Text))

Max Activating Token Index: 987