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

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

Neuron 2660 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2717. Min Act: -0.0001

Data Index: 204468 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2709. Min Act: -0.0001

Data Index: 788309 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2957. Min Act: -0.0001

Data Index: 884137 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2758. Min Act: -0.0001

Data Index: 239441 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2604. Min Act: -0.0001

Data Index: 564318 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1268647 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2452. Min Act: -0.0001

Data Index: 366764 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2768. Min Act: -0.0001

Data Index: 459894 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2311. Min Act: -0.0001

Data Index: 824034 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2359. Min Act: -0.0001

Data Index: 812853 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2413. Min Act: -0.0001

Data Index: 104623 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2300. Min Act: -0.0001

Data Index: 802795 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1152077 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2449. Min Act: -0.0001

Data Index: 419977 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2101. Min Act: -0.0001

Data Index: 200951 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2477. Min Act: -0.0001

Data Index: 1093012 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2219. Min Act: -0.0001

Data Index: 354383 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2057. Min Act: -0.0001

Data Index: 765315 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2358. Min Act: -0.0001

Data Index: 823468 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1332834 (C4 (Web Text))

Max Activating Token Index: 127