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

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

Neuron 4772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.7634. Min Act: -0.0000

Data Index: 442467 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6502. Min Act: -0.0000

Data Index: 311277 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6745. Min Act: -0.0001

Data Index: 748701 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6474. Min Act: -0.0000

Data Index: 397776 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.7252. Min Act: -0.0001

Data Index: 1192493 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5832. Min Act: -0.0001

Data Index: 648336 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6090. Min Act: -0.0000

Data Index: 143014 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.6301. Min Act: -0.0000

Data Index: 3012 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1173240 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1049808 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5797. Min Act: -0.0000

Data Index: 361802 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1098703 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5193. Min Act: -0.0001

Data Index: 175547 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5840. Min Act: -0.0001

Data Index: 893568 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5455. Min Act: -0.0000

Data Index: 200688 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5234. Min Act: -0.0000

Data Index: 881448 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5187. Min Act: -0.0000

Data Index: 704109 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1314223 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.5569. Min Act: -0.0000

Data Index: 435557 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.7634. Min Range: -0.7634

Max Act: 0.4753. Min Act: -0.0000

Data Index: 540918 (C4 (Web Text))

Max Activating Token Index: 824