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

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

Neuron 3357 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.9474. Min Act: -0.0001

Data Index: 954852 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.9733. Min Act: -0.0000

Data Index: 30528 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7485. Min Act: -0.0001

Data Index: 1047083 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7590. Min Act: -0.0001

Data Index: 981784 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.9095. Min Act: -0.0001

Data Index: 1015465 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.8357. Min Act: -0.0001

Data Index: 108767 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.8640. Min Act: -0.0001

Data Index: 981257 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.6940. Min Act: -0.0001

Data Index: 878939 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.6742. Min Act: -0.0001

Data Index: 98696 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7638. Min Act: -0.0001

Data Index: 1305339 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7448. Min Act: -0.0001

Data Index: 657046 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.6706. Min Act: -0.0001

Data Index: 1065599 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7072. Min Act: -0.0001

Data Index: 520308 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.7166. Min Act: -0.0001

Data Index: 328393 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.6725. Min Act: -0.0001

Data Index: 1049370 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.6304. Min Act: -0.0001

Data Index: 198828 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.5897. Min Act: -0.0001

Data Index: 491812 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.6195. Min Act: -0.0001

Data Index: 192391 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.5669. Min Act: -0.0000

Data Index: 1095431 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.9733. Min Range: -1.9733

Max Act: 1.5654. Min Act: -0.0001

Data Index: 1243927 (C4 (Web Text))

Max Activating Token Index: 354