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

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

Neuron 5321 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: 1.5923. Min Range: -1.5923

Max Act: 1.5923. Min Act: 0.0000

Data Index: 150921 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.4873. Min Act: -0.0000

Data Index: 755697 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.4628. Min Act: -0.0000

Data Index: 989566 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1141257 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.2725. Min Act: -0.0000

Data Index: 888485 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.3338. Min Act: -0.0000

Data Index: 591865 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.2382. Min Act: -0.0000

Data Index: 575776 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.1915. Min Act: -0.0000

Data Index: 850310 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.1918. Min Act: -0.0000

Data Index: 967911 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.1754. Min Act: -0.0000

Data Index: 400099 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.1588. Min Act: -0.0000

Data Index: 529754 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.2257. Min Act: -0.0000

Data Index: 772590 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.1281. Min Act: -0.0000

Data Index: 998407 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0838. Min Act: -0.0000

Data Index: 950073 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0705. Min Act: -0.0000

Data Index: 611437 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0637. Min Act: -0.0000

Data Index: 116584 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.1288. Min Act: -0.0000

Data Index: 22916 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9721. Min Act: -0.0000

Data Index: 917755 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0163. Min Act: -0.0000

Data Index: 581459 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0658. Min Act: -0.0000

Data Index: 552611 (C4 (Web Text))

Max Activating Token Index: 122