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

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

Neuron 4154 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.9222. Min Act: -0.0001

Data Index: 1021491 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8284. Min Act: -0.0001

Data Index: 542090 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7778. Min Act: -0.0001

Data Index: 808581 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.8037. Min Act: -0.0001

Data Index: 840665 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6563. Min Act: -0.0001

Data Index: 772775 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7196. Min Act: -0.0001

Data Index: 1111051 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7131. Min Act: -0.0001

Data Index: 896220 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6427. Min Act: -0.0001

Data Index: 45203 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6860. Min Act: -0.0001

Data Index: 501565 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7386. Min Act: -0.0001

Data Index: 254950 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6748. Min Act: -0.0001

Data Index: 271969 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6469. Min Act: -0.0001

Data Index: 459703 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.7519. Min Act: -0.0001

Data Index: 1103847 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6243. Min Act: -0.0001

Data Index: 1111039 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6725. Min Act: -0.0001

Data Index: 411653 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1221957 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6417. Min Act: -0.0001

Data Index: 1048831 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6533. Min Act: -0.0001

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6488. Min Act: -0.0001

Data Index: 545523 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.9222. Min Range: -0.9222

Max Act: 0.6523. Min Act: -0.0001

Data Index: 594016 (C4 (Web Text))

Max Activating Token Index: 364