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

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

Neuron 3466 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1466. Min Range: -1.1466

Max Act: 1.1466. Min Act: -0.0000

Data Index: 538454 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.9336. Min Act: -0.0000

Data Index: 758360 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1053756 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.7327. Min Act: -0.0000

Data Index: 255142 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.7352. Min Act: -0.0000

Data Index: 999724 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6915. Min Act: -0.0000

Data Index: 248364 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1220077 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6595. Min Act: -0.0000

Data Index: 102409 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1341131 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6394. Min Act: -0.0000

Data Index: 445347 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6737. Min Act: -0.0000

Data Index: 588940 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6202. Min Act: -0.0000

Data Index: 531386 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6236. Min Act: -0.0000

Data Index: 961446 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.5943. Min Act: -0.0000

Data Index: 297480 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6369. Min Act: -0.0000

Data Index: 941155 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.5849. Min Act: -0.0000

Data Index: 871513 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1148818 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.5447. Min Act: -0.0000

Data Index: 777165 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6212. Min Act: -0.0000

Data Index: 679442 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 1.1466. Min Range: -1.1466

Max Act: 0.6009. Min Act: -0.0000

Data Index: 604671 (C4 (Web Text))

Max Activating Token Index: 246