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

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

Neuron 3753 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4317. Min Act: -0.0000

Data Index: 306661 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4134. Min Act: -0.0000

Data Index: 606621 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1130101 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4685. Min Act: -0.0000

Data Index: 568127 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.3502. Min Act: -0.0000

Data Index: 809752 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.3428. Min Act: -0.0000

Data Index: 190233 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1308835 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.3346. Min Act: -0.0000

Data Index: 226064 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2994. Min Act: -0.0000

Data Index: 564471 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1208907 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1176855 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1279717 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2696. Min Act: -0.0000

Data Index: 909275 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2694. Min Act: -0.0000

Data Index: 317811 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1130637 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2275. Min Act: -0.0000

Data Index: 372893 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1100322 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2136. Min Act: -0.0000

Data Index: 22977 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1322405 (C4 (Web Text))

Max Activating Token Index: 450