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

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

Neuron 4107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7707. Min Range: -4.7707

Max Act: 4.7707. Min Act: -0.0000

Data Index: 191237 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 4.7707. Min Range: -4.7707

Max Act: 4.6364. Min Act: -0.0000

Data Index: 205945 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.9194. Min Act: -0.0000

Data Index: 5004 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.6698. Min Act: -0.0000

Data Index: 151571 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.8120. Min Act: -0.0000

Data Index: 688707 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.6471. Min Act: -0.0000

Data Index: 1250486 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.4480. Min Act: -0.0000

Data Index: 1119496 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.3998. Min Act: -0.0000

Data Index: 856853 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.3248. Min Act: -0.0000

Data Index: 944107 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.5966. Min Act: -0.0000

Data Index: 852450 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.3739. Min Act: -0.0000

Data Index: 704029 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.3546. Min Act: -0.0000

Data Index: 498407 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.5143. Min Act: -0.0000

Data Index: 489225 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.2971. Min Act: -0.0000

Data Index: 771990 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.2234. Min Act: -0.0000

Data Index: 1299003 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.0801. Min Act: -0.0000

Data Index: 896191 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.1793. Min Act: -0.0000

Data Index: 123256 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.1492. Min Act: -0.0000

Data Index: 645574 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.1210. Min Act: -0.0000

Data Index: 680401 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 4.7707. Min Range: -4.7707

Max Act: 3.2582. Min Act: -0.0000

Data Index: 1050067 (C4 (Web Text))

Max Activating Token Index: 123