Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2527 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0811. Min Range: -1.0811

Max Act: 1.0811. Min Act: -0.0000

Data Index: 864454 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8827. Min Act: -0.0000

Data Index: 514553 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.7682. Min Act: -0.0000

Data Index: 435580 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.8063. Min Act: -0.0000

Data Index: 175295 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1245281 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.7709. Min Act: -0.0000

Data Index: 14902 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.7193. Min Act: -0.0000

Data Index: 294652 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1055456 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.6782. Min Act: 0.0000

Data Index: 401585 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1067964 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.7134. Min Act: -0.0000

Data Index: 186097 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1033639 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1110966 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.6412. Min Act: -0.0000

Data Index: 996785 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.6515. Min Act: -0.0001

Data Index: 123498 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.6117. Min Act: -0.0001

Data Index: 147798 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.6312. Min Act: -0.0000

Data Index: 642591 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.5879. Min Act: -0.0000

Data Index: 602004 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1224415 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.0811. Min Range: -1.0811

Max Act: 0.5786. Min Act: -0.0001

Data Index: 411851 (C4 (Web Text))

Max Activating Token Index: 191