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

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

Neuron 5927 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: 1.6826. Min Range: -1.6826

Max Act: 1.6826. Min Act: -0.0000

Data Index: 1349156 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1164128 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6765. Min Act: -0.0000

Data Index: 735227 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5324. Min Act: -0.0000

Data Index: 332880 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.3668. Min Act: -0.0000

Data Index: 617081 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1187856 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1240302 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.0877. Min Act: -0.0000

Data Index: 474684 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1350799 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.0885. Min Act: -0.0000

Data Index: 628903 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.1441. Min Act: -0.0000

Data Index: 757964 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.0493. Min Act: -0.0000

Data Index: 335777 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1008519 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.6826. Min Range: -1.6826

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1254063 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.6826. Min Range: -1.6826

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1011581 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.6826. Min Range: -1.6826

Max Act: 0.9523. Min Act: -0.0000

Data Index: 508637 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.6826. Min Range: -1.6826

Max Act: 0.9355. Min Act: -0.0000

Data Index: 404336 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.6826. Min Range: -1.6826

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1028734 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.6826. Min Range: -1.6826

Max Act: 0.9275. Min Act: -0.0000

Data Index: 349130 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 1.6826. Min Range: -1.6826

Max Act: 0.9200. Min Act: -0.0000

Data Index: 7676 (C4 (Web Text))

Max Activating Token Index: 164