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

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

Neuron 3004 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3503. Min Act: -0.0000

Data Index: 183988 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3217. Min Act: -0.0000

Data Index: 967808 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2985. Min Act: -0.0000

Data Index: 279989 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3087. Min Act: -0.0000

Data Index: 598180 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3062. Min Act: -0.0000

Data Index: 535657 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3054. Min Act: -0.0000

Data Index: 176986 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2888. Min Act: -0.0000

Data Index: 825509 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3286. Min Act: -0.0000

Data Index: 903446 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1073994 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3027. Min Act: -0.0000

Data Index: 622689 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3124. Min Act: -0.0000

Data Index: 303838 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2998. Min Act: -0.0000

Data Index: 21318 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3003. Min Act: -0.0000

Data Index: 31180 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3068. Min Act: -0.0000

Data Index: 521778 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3047. Min Act: -0.0000

Data Index: 240309 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2998. Min Act: -0.0000

Data Index: 797047 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2628. Min Act: -0.0000

Data Index: 708203 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1160338 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1116186 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2543. Min Act: -0.0000

Data Index: 270407 (C4 (Web Text))

Max Activating Token Index: 36