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

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

Neuron 84 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9792. Min Act: -0.0001

Data Index: 1173414 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9336. Min Act: -0.0001

Data Index: 1138123 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9046. Min Act: -0.0001

Data Index: 839369 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9584. Min Act: -0.0001

Data Index: 429461 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8603. Min Act: -0.0001

Data Index: 203665 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8272. Min Act: -0.0001

Data Index: 616291 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8491. Min Act: -0.0001

Data Index: 15321 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8736. Min Act: -0.0001

Data Index: 919975 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8218. Min Act: -0.0001

Data Index: 719142 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7887. Min Act: -0.0001

Data Index: 706932 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8112. Min Act: -0.0001

Data Index: 194684 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8111. Min Act: -0.0001

Data Index: 15504 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8367. Min Act: -0.0001

Data Index: 965759 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8308. Min Act: -0.0001

Data Index: 1139606 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7891. Min Act: -0.0001

Data Index: 1145045 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7742. Min Act: -0.0001

Data Index: 218034 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8119. Min Act: -0.0001

Data Index: 146312 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8371. Min Act: -0.0001

Data Index: 169991 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7536. Min Act: -0.0001

Data Index: 310386 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7852. Min Act: -0.0001

Data Index: 184896 (C4 (Web Text))

Max Activating Token Index: 714