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

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

Neuron 75 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.8720. Min Act: -0.0000

Data Index: 1207342 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.7594. Min Act: -0.0000

Data Index: 201283 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.3487. Min Act: -0.0000

Data Index: 1189771 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.9682. Min Act: -0.0000

Data Index: 1184252 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.9335. Min Act: -0.0000

Data Index: 766444 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.7517. Min Act: -0.0000

Data Index: 240102 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.2848. Min Act: -0.0000

Data Index: 675660 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.3132. Min Act: -0.0000

Data Index: 681426 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.2334. Min Act: -0.0000

Data Index: 192524 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.0967. Min Act: -0.0000

Data Index: 1076771 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.1812. Min Act: -0.0000

Data Index: 663697 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1169714 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.1241. Min Act: -0.0000

Data Index: 537312 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.1120. Min Act: 0.0000

Data Index: 780699 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.1556. Min Act: -0.0000

Data Index: 1148581 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.0466. Min Act: -0.0000

Data Index: 301850 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.0954. Min Act: -0.0000

Data Index: 278950 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 3.8720. Min Range: -3.8720

Max Act: 1.0088. Min Act: -0.0000

Data Index: 518899 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 3.8720. Min Range: -3.8720

Max Act: 0.9874. Min Act: -0.0000

Data Index: 890669 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.8720. Min Range: -3.8720

Max Act: 0.9779. Min Act: -0.0000

Data Index: 403947 (C4 (Web Text))

Max Activating Token Index: 541