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

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

Neuron 2530 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4667. Min Range: -2.4667

Max Act: 2.4667. Min Act: -0.0000

Data Index: 22456 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 2.4667. Min Range: -2.4667

Max Act: 2.4244. Min Act: -0.0000

Data Index: 1240186 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 2.4667. Min Range: -2.4667

Max Act: 2.2473. Min Act: -0.0000

Data Index: 68099 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.7509. Min Act: -0.0000

Data Index: 912979 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.6245. Min Act: -0.0000

Data Index: 1185461 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.5442. Min Act: -0.0000

Data Index: 834045 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.4823. Min Act: -0.0000

Data Index: 611096 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.4809. Min Act: -0.0000

Data Index: 663045 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.3950. Min Act: -0.0000

Data Index: 834611 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.5262. Min Act: -0.0000

Data Index: 530076 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.4034. Min Act: -0.0000

Data Index: 1298726 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1299376 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.3496. Min Act: -0.0000

Data Index: 147051 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1053142 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.3289. Min Act: -0.0000

Data Index: 1279706 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.4019. Min Act: -0.0000

Data Index: 120364 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.3740. Min Act: -0.0000

Data Index: 861250 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.2642. Min Act: -0.0000

Data Index: 329162 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1259209 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1296455 (C4 (Web Text))

Max Activating Token Index: 483