Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5301 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.5104. Min Act: -0.0000

Data Index: 534824 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.4825. Min Act: -0.0000

Data Index: 1593097 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1442287 (Python Code)

Max Activating Token Index: 304

Text #3

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.2659. Min Act: -0.0000

Data Index: 742359 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.1680. Min Act: -0.0000

Data Index: 680960 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1567286 (Python Code)

Max Activating Token Index: 627

Text #6

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1438442 (Python Code)

Max Activating Token Index: 1021

Text #7

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1477157 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 1.5304. Min Range: -1.5304

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1495653 (Python Code)

Max Activating Token Index: 484

Text #9

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.0787. Min Act: -0.0000

Data Index: 467599 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1641404 (Python Code)

Max Activating Token Index: 878

Text #11

Max Range: 1.5304. Min Range: -1.5304

Max Act: 0.9733. Min Act: -0.0000

Data Index: 69102 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1532411 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 1.5304. Min Range: -1.5304

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1419316 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 1.5304. Min Range: -1.5304

Max Act: 0.9752. Min Act: -0.0000

Data Index: 14868 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.5304. Min Range: -1.5304

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1594968 (Python Code)

Max Activating Token Index: 422

Text #16

Max Range: 1.5304. Min Range: -1.5304

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1413168 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.0330. Min Act: 0.0000

Data Index: 237213 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.5304. Min Range: -1.5304

Max Act: 0.9747. Min Act: -0.0000

Data Index: 699331 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1459085 (Python Code)

Max Activating Token Index: 730