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

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

Neuron 372 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1307913 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8330. Min Act: -0.0000

Data Index: 301965 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7942. Min Act: -0.0000

Data Index: 502305 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8571. Min Act: -0.0000

Data Index: 726812 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7840. Min Act: -0.0000

Data Index: 126932 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8549. Min Act: -0.0000

Data Index: 254017 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1140161 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7806. Min Act: -0.0000

Data Index: 130660 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7388. Min Act: -0.0000

Data Index: 829229 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1169565 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7476. Min Act: -0.0000

Data Index: 410968 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1248310 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1179144 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6637. Min Act: -0.0000

Data Index: 301889 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1053012 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6813. Min Act: -0.0000

Data Index: 775460 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7122. Min Act: -0.0000

Data Index: 673426 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7447. Min Act: -0.0000

Data Index: 873123 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6741. Min Act: -0.0000

Data Index: 425660 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6678. Min Act: -0.0000

Data Index: 65984 (C4 (Web Text))

Max Activating Token Index: 256