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

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

Neuron 1571 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.6765. Min Act: -0.0000

Data Index: 393029 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.5356. Min Act: -0.0000

Data Index: 641635 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3839. Min Act: -0.0000

Data Index: 177540 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3286. Min Act: -0.0000

Data Index: 353914 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1347834 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3054. Min Act: -0.0000

Data Index: 388338 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.2262. Min Act: -0.0001

Data Index: 681272 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.2368. Min Act: -0.0000

Data Index: 887301 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.2279. Min Act: -0.0000

Data Index: 239983 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1480. Min Act: -0.0000

Data Index: 603036 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3576. Min Act: -0.0000

Data Index: 130304 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1140. Min Act: -0.0000

Data Index: 708486 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1789. Min Act: -0.0000

Data Index: 837393 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1896. Min Act: -0.0000

Data Index: 264997 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.0866. Min Act: -0.0000

Data Index: 437881 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1999. Min Act: -0.0000

Data Index: 987600 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.0934. Min Act: -0.0000

Data Index: 115720 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1102224 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1076. Min Act: -0.0000

Data Index: 665883 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1295898 (C4 (Web Text))

Max Activating Token Index: 500