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

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

Neuron 4467 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1158839 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.3041. Min Act: -0.0000

Data Index: 287655 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1305978 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.3006. Min Act: -0.0000

Data Index: 973174 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1146978 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1195935 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1186941 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2754. Min Act: -0.0000

Data Index: 619150 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2944. Min Act: -0.0000

Data Index: 455382 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2833. Min Act: -0.0000

Data Index: 74710 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1213721 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1275004 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2673. Min Act: -0.0000

Data Index: 836494 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2578. Min Act: -0.0000

Data Index: 346384 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1160925 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2693. Min Act: -0.0000

Data Index: 256595 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2472. Min Act: -0.0000

Data Index: 854041 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1357695 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2506. Min Act: -0.0000

Data Index: 204332 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2265. Min Act: -0.0000

Data Index: 398147 (C4 (Web Text))

Max Activating Token Index: 334