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

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

Neuron 4762 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7151. Min Range: -3.7151

Max Act: 3.7151. Min Act: -0.0000

Data Index: 215051 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.7151. Min Range: -3.7151

Max Act: 3.4644. Min Act: -0.0000

Data Index: 884356 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 3.7151. Min Range: -3.7151

Max Act: 3.0258. Min Act: -0.0000

Data Index: 657663 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.9405. Min Act: -0.0000

Data Index: 1332733 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.7151. Min Range: -3.7151

Max Act: 3.3055. Min Act: -0.0000

Data Index: 690507 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 3.7151. Min Range: -3.7151

Max Act: 3.1800. Min Act: -0.0000

Data Index: 907379 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.9899. Min Act: -0.0000

Data Index: 249123 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.9017. Min Act: -0.0000

Data Index: 1217711 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.8740. Min Act: -0.0000

Data Index: 735910 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.7504. Min Act: -0.0000

Data Index: 806619 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.6158. Min Act: -0.0000

Data Index: 1317707 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.6837. Min Act: -0.0000

Data Index: 740705 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.5630. Min Act: -0.0000

Data Index: 1286435 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.5346. Min Act: -0.0000

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.5607. Min Act: -0.0000

Data Index: 295940 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.5081. Min Act: -0.0000

Data Index: 70163 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.4233. Min Act: -0.0000

Data Index: 344140 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.4420. Min Act: -0.0000

Data Index: 1287889 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.5310. Min Act: -0.0000

Data Index: 221362 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 3.7151. Min Range: -3.7151

Max Act: 2.6523. Min Act: -0.0000

Data Index: 785698 (C4 (Web Text))

Max Activating Token Index: 85