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

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

Neuron 4032 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: 0.9918. Min Range: -0.9918

Max Act: 0.9918. Min Act: -0.0001

Data Index: 1019100 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7803. Min Act: -0.0000

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6978. Min Act: -0.0001

Data Index: 99699 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6916. Min Act: -0.0001

Data Index: 1280213 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6522. Min Act: -0.0000

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6348. Min Act: -0.0001

Data Index: 508761 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1273923 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5280. Min Act: -0.0001

Data Index: 172803 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5646. Min Act: -0.0000

Data Index: 48663 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5514. Min Act: -0.0001

Data Index: 345684 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5940. Min Act: -0.0001

Data Index: 36482 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5633. Min Act: -0.0000

Data Index: 263842 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5656. Min Act: -0.0000

Data Index: 647701 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5684. Min Act: -0.0001

Data Index: 89096 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5814. Min Act: -0.0000

Data Index: 571098 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.4813. Min Act: -0.0001

Data Index: 249686 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5676. Min Act: -0.0001

Data Index: 917100 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1127989 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6009. Min Act: -0.0001

Data Index: 281862 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5184. Min Act: -0.0000

Data Index: 297880 (C4 (Web Text))

Max Activating Token Index: 217