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

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

Neuron 5077 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.2579. Min Act: 0.0000

Data Index: 1150290 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1737. Min Act: -0.0000

Data Index: 721406 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1695. Min Act: 0.0000

Data Index: 1034288 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0342. Min Act: -0.0000

Data Index: 961783 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9864. Min Act: -0.0000

Data Index: 790750 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9769. Min Act: 0.0000

Data Index: 445277 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9400. Min Act: -0.0000

Data Index: 114095 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9296. Min Act: 0.0000

Data Index: 24825 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.9360. Min Act: -0.0000

Data Index: 330608 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8362. Min Act: -0.0000

Data Index: 238333 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8532. Min Act: -0.0000

Data Index: 742638 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8542. Min Act: -0.0000

Data Index: 837813 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8239. Min Act: -0.0000

Data Index: 237682 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8619. Min Act: -0.0000

Data Index: 627216 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8150. Min Act: -0.0000

Data Index: 539340 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8438. Min Act: -0.0000

Data Index: 125534 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.7102. Min Act: -0.0000

Data Index: 690913 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.8262. Min Act: -0.0000

Data Index: 85000 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.7973. Min Act: 0.0000

Data Index: 1124283 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.2579. Min Range: -1.2579

Max Act: 0.7502. Min Act: -0.0000

Data Index: 721919 (C4 (Web Text))

Max Activating Token Index: 464