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

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

Neuron 46 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.6421. Min Act: -0.0000

Data Index: 393264 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.3786. Min Act: -0.0000

Data Index: 231979 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.1952. Min Act: -0.0000

Data Index: 800182 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9683. Min Act: -0.0000

Data Index: 172466 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.0065. Min Act: -0.0001

Data Index: 682909 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9216. Min Act: -0.0000

Data Index: 37674 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9775. Min Act: -0.0000

Data Index: 490377 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9103. Min Act: -0.0000

Data Index: 214902 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1157616 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8832. Min Act: -0.0001

Data Index: 260950 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1052975 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8175. Min Act: -0.0000

Data Index: 1442273 (Python Code)

Max Activating Token Index: 581

Text #12

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8111. Min Act: -0.0000

Data Index: 505903 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8066. Min Act: -0.0000

Data Index: 699578 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.7743. Min Act: -0.0000

Data Index: 960620 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1020847 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1083753 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8026. Min Act: -0.0000

Data Index: 70629 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1024724 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.7304. Min Act: -0.0000

Data Index: 751994 (C4 (Web Text))

Max Activating Token Index: 492