Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2832 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1200766 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.5979. Min Act: -0.0000

Data Index: 889339 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.5840. Min Act: -0.0000

Data Index: 181689 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4966. Min Act: -0.0000

Data Index: 614572 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.5042. Min Act: -0.0000

Data Index: 626440 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4845. Min Act: -0.0000

Data Index: 830521 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1334702 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4878. Min Act: -0.0000

Data Index: 233235 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4945. Min Act: -0.0000

Data Index: 336384 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1262287 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4651. Min Act: -0.0000

Data Index: 811216 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1182180 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4419. Min Act: -0.0000

Data Index: 201656 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4386. Min Act: -0.0000

Data Index: 85015 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4447. Min Act: -0.0000

Data Index: 881195 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1045204 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4131. Min Act: -0.0000

Data Index: 243556 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1229146 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4284. Min Act: -0.0000

Data Index: 603866 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4161. Min Act: -0.0000

Data Index: 882846 (C4 (Web Text))

Max Activating Token Index: 471