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

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

Neuron 2078 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: 1.2393. Min Range: -1.2393

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1023003 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.2196. Min Act: -0.0000

Data Index: 844296 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1706. Min Act: -0.0000

Data Index: 179015 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1731. Min Act: -0.0000

Data Index: 542733 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1673. Min Act: 0.0000

Data Index: 1337844 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1460. Min Act: -0.0000

Data Index: 73690 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1055. Min Act: -0.0000

Data Index: 138968 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1713. Min Act: -0.0000

Data Index: 422929 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.0922. Min Act: -0.0000

Data Index: 804170 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1415. Min Act: -0.0000

Data Index: 724494 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.0739. Min Act: -0.0000

Data Index: 324360 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.0906. Min Act: -0.0000

Data Index: 749691 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.0233. Min Act: -0.0000

Data Index: 406001 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1249. Min Act: -0.0000

Data Index: 912624 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.0537. Min Act: -0.0000

Data Index: 815248 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1129897 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.0548. Min Act: -0.0000

Data Index: 857747 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.0483. Min Act: -0.0000

Data Index: 695021 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1165. Min Act: -0.0000

Data Index: 539501 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.0756. Min Act: -0.0000

Data Index: 377572 (C4 (Web Text))

Max Activating Token Index: 246