Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5187 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2539. Min Range: -2.2539

Max Act: 2.2539. Min Act: -0.0000

Data Index: 37281 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 2.2539. Min Range: -2.2539

Max Act: 2.0173. Min Act: -0.0000

Data Index: 215372 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.7824. Min Act: -0.0000

Data Index: 811578 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.7496. Min Act: -0.0000

Data Index: 1004111 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.7162. Min Act: -0.0000

Data Index: 738276 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.6826. Min Act: -0.0000

Data Index: 549104 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.5762. Min Act: -0.0000

Data Index: 1486742 (Python Code)

Max Activating Token Index: 692

Text #7

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.6718. Min Act: -0.0000

Data Index: 1458715 (Python Code)

Max Activating Token Index: 901

Text #8

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1087541 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.6516. Min Act: -0.0000

Data Index: 641778 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.6309. Min Act: -0.0000

Data Index: 116099 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.6878. Min Act: -0.0000

Data Index: 916742 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.5838. Min Act: -0.0000

Data Index: 81428 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.6829. Min Act: -0.0000

Data Index: 834080 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.5893. Min Act: -0.0000

Data Index: 1144481 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.5549. Min Act: -0.0000

Data Index: 1260738 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.6311. Min Act: -0.0000

Data Index: 506029 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.5516. Min Act: -0.0000

Data Index: 1164810 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.5105. Min Act: -0.0000

Data Index: 286735 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 2.2539. Min Range: -2.2539

Max Act: 1.4160. Min Act: -0.0000

Data Index: 755455 (C4 (Web Text))

Max Activating Token Index: 301