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

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

Neuron 1907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0731. Min Range: -1.0731

Max Act: 1.0731. Min Act: -0.0001

Data Index: 1251838 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 1.0731. Min Range: -1.0731

Max Act: 1.0396. Min Act: -0.0001

Data Index: 462954 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 1.0731. Min Range: -1.0731

Max Act: 1.0057. Min Act: -0.0001

Data Index: 509330 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.0731. Min Range: -1.0731

Max Act: 1.0104. Min Act: -0.0001

Data Index: 579296 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9880. Min Act: -0.0001

Data Index: 729376 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.0731. Min Range: -1.0731

Max Act: 1.0043. Min Act: -0.0001

Data Index: 528850 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9779. Min Act: -0.0001

Data Index: 1142930 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9156. Min Act: -0.0001

Data Index: 490355 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9415. Min Act: -0.0001

Data Index: 914382 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8973. Min Act: -0.0001

Data Index: 1384594 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9151. Min Act: -0.0001

Data Index: 388110 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1047665 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9041. Min Act: -0.0001

Data Index: 532883 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8743. Min Act: -0.0001

Data Index: 1293979 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8809. Min Act: -0.0001

Data Index: 55363 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8849. Min Act: -0.0001

Data Index: 1243842 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8976. Min Act: -0.0001

Data Index: 698487 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8144. Min Act: -0.0001

Data Index: 1074105 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.9268. Min Act: -0.0001

Data Index: 1051331 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.0731. Min Range: -1.0731

Max Act: 0.8659. Min Act: -0.0001

Data Index: 942509 (C4 (Web Text))

Max Activating Token Index: 447