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

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

Neuron 4984 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0312. Min Range: -1.0312

Max Act: 1.0312. Min Act: -0.0001

Data Index: 969999 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8522. Min Act: -0.0001

Data Index: 495319 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8335. Min Act: -0.0001

Data Index: 204200 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7826. Min Act: -0.0001

Data Index: 1291361 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7749. Min Act: -0.0001

Data Index: 321100 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7868. Min Act: -0.0001

Data Index: 446946 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7185. Min Act: -0.0001

Data Index: 800631 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7596. Min Act: -0.0001

Data Index: 711567 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6348. Min Act: -0.0001

Data Index: 974407 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7332. Min Act: -0.0001

Data Index: 1248539 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6899. Min Act: -0.0001

Data Index: 763891 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6866. Min Act: -0.0001

Data Index: 748970 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7372. Min Act: -0.0001

Data Index: 1066370 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6724. Min Act: -0.0001

Data Index: 1028444 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6477. Min Act: -0.0001

Data Index: 279815 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6721. Min Act: -0.0001

Data Index: 456018 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7062. Min Act: -0.0001

Data Index: 719857 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6580. Min Act: -0.0001

Data Index: 929646 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6823. Min Act: -0.0001

Data Index: 382303 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.5936. Min Act: -0.0001

Data Index: 491836 (C4 (Web Text))

Max Activating Token Index: 365