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

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

Neuron 2941 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5682. Min Act: -0.0000

Data Index: 113945 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5104. Min Act: -0.0000

Data Index: 978379 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2889. Min Act: -0.0000

Data Index: 284319 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2938. Min Act: -0.0000

Data Index: 869834 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5232. Min Act: -0.0000

Data Index: 736934 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2660. Min Act: -0.0000

Data Index: 793984 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.3639. Min Act: -0.0000

Data Index: 771244 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2974. Min Act: -0.0000

Data Index: 535606 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2769. Min Act: -0.0000

Data Index: 1028103 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0825. Min Act: -0.0000

Data Index: 132592 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1280. Min Act: -0.0000

Data Index: 494894 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1838. Min Act: -0.0000

Data Index: 275201 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0406. Min Act: -0.0000

Data Index: 32912 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1031904 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.5682. Min Range: -1.5682

Max Act: 0.9779. Min Act: -0.0000

Data Index: 97735 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2119. Min Act: -0.0000

Data Index: 227441 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1078331 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0865. Min Act: -0.0000

Data Index: 270588 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0776. Min Act: -0.0000

Data Index: 730225 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0378. Min Act: -0.0000

Data Index: 464802 (C4 (Web Text))

Max Activating Token Index: 680