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

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

Neuron 1930 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.8422. Min Act: -0.0001

Data Index: 217546 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.7490. Min Act: -0.0001

Data Index: 777570 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.7972. Min Act: -0.0001

Data Index: 216755 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.7359. Min Act: -0.0001

Data Index: 1243004 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6998. Min Act: -0.0001

Data Index: 658621 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1292966 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.7286. Min Act: -0.0001

Data Index: 1164497 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6806. Min Act: -0.0001

Data Index: 1314882 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6154. Min Act: -0.0001

Data Index: 513036 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6795. Min Act: -0.0001

Data Index: 1017184 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6628. Min Act: -0.0001

Data Index: 546918 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.7260. Min Act: -0.0001

Data Index: 399566 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6301. Min Act: -0.0001

Data Index: 213002 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6279. Min Act: -0.0001

Data Index: 29206 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6389. Min Act: -0.0001

Data Index: 193855 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6535. Min Act: -0.0001

Data Index: 200348 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6226. Min Act: -0.0001

Data Index: 700295 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6036. Min Act: -0.0001

Data Index: 1005819 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1276239 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.8422. Min Range: -0.8422

Max Act: 0.6147. Min Act: -0.0001

Data Index: 897704 (C4 (Web Text))

Max Activating Token Index: 938