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

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

Neuron 5972 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7254. Min Range: -2.7254

Max Act: 2.7254. Min Act: -0.0000

Data Index: 1244140 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 2.7254. Min Range: -2.7254

Max Act: 2.2646. Min Act: -0.0000

Data Index: 294999 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 2.7254. Min Range: -2.7254

Max Act: 2.3597. Min Act: -0.0000

Data Index: 691349 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 2.7254. Min Range: -2.7254

Max Act: 2.0789. Min Act: -0.0000

Data Index: 1326033 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 2.7254. Min Range: -2.7254

Max Act: 2.1666. Min Act: -0.0000

Data Index: 583537 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 2.7254. Min Range: -2.7254

Max Act: 2.1499. Min Act: -0.0000

Data Index: 668726 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.9781. Min Act: -0.0000

Data Index: 1127241 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 2.7254. Min Range: -2.7254

Max Act: 2.1383. Min Act: -0.0000

Data Index: 1262143 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.9252. Min Act: -0.0000

Data Index: 19136 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.9018. Min Act: -0.0000

Data Index: 18992 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.8433. Min Act: -0.0000

Data Index: 899425 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.7749. Min Act: -0.0000

Data Index: 795939 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.8778. Min Act: -0.0000

Data Index: 402100 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.6347. Min Act: -0.0000

Data Index: 81823 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.7887. Min Act: -0.0000

Data Index: 1320943 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.7625. Min Act: -0.0000

Data Index: 1061634 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.7436. Min Act: -0.0000

Data Index: 377525 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.6079. Min Act: -0.0000

Data Index: 360544 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.5071. Min Act: -0.0000

Data Index: 215290 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 2.7254. Min Range: -2.7254

Max Act: 1.5017. Min Act: -0.0000

Data Index: 37654 (C4 (Web Text))

Max Activating Token Index: 339