Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3816 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3151. Min Range: -2.3151

Max Act: 2.3151. Min Act: -0.0000

Data Index: 492354 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.9540. Min Act: -0.0000

Data Index: 1308610 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 2.3151. Min Range: -2.3151

Max Act: 2.2628. Min Act: -0.0000

Data Index: 344619 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 2.3151. Min Range: -2.3151

Max Act: 2.0806. Min Act: -0.0000

Data Index: 539494 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.8289. Min Act: -0.0000

Data Index: 1036560 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 2.3151. Min Range: -2.3151

Max Act: 2.0332. Min Act: -0.0000

Data Index: 531681 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.9033. Min Act: -0.0000

Data Index: 1321158 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.8806. Min Act: -0.0000

Data Index: 462802 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.7719. Min Act: -0.0000

Data Index: 573425 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.7015. Min Act: -0.0000

Data Index: 164408 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.8965. Min Act: -0.0000

Data Index: 245585 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.7623. Min Act: -0.0000

Data Index: 179402 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.6095. Min Act: -0.0000

Data Index: 48970 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.7762. Min Act: -0.0000

Data Index: 1050215 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.5787. Min Act: -0.0000

Data Index: 672254 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.6676. Min Act: -0.0000

Data Index: 268164 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.5648. Min Act: -0.0000

Data Index: 1154529 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.5904. Min Act: -0.0000

Data Index: 479128 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.5035. Min Act: -0.0000

Data Index: 397380 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 2.3151. Min Range: -2.3151

Max Act: 1.4784. Min Act: -0.0000

Data Index: 415948 (C4 (Web Text))

Max Activating Token Index: 32