Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1126 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6793. Min Act: -0.0001

Data Index: 23396 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6786. Min Act: -0.0001

Data Index: 1287485 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.7020. Min Act: -0.0001

Data Index: 200321 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6765. Min Act: -0.0001

Data Index: 649189 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6801. Min Act: -0.0001

Data Index: 900990 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.7036. Min Act: -0.0001

Data Index: 707440 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6524. Min Act: -0.0001

Data Index: 853729 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6465. Min Act: -0.0001

Data Index: 832621 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6639. Min Act: -0.0001

Data Index: 459834 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6268. Min Act: -0.0001

Data Index: 912131 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6228. Min Act: -0.0001

Data Index: 416710 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6173. Min Act: -0.0001

Data Index: 1115234 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6345. Min Act: -0.0001

Data Index: 100544 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6350. Min Act: -0.0001

Data Index: 218955 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6332. Min Act: -0.0001

Data Index: 1001923 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5762. Min Act: -0.0001

Data Index: 931087 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6228. Min Act: -0.0001

Data Index: 282851 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5840. Min Act: -0.0001

Data Index: 1009455 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6630. Min Act: -0.0001

Data Index: 710896 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5949. Min Act: -0.0001

Data Index: 286335 (C4 (Web Text))

Max Activating Token Index: 932