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

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

Neuron 5664 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: 3.9111. Min Range: -3.9111

Max Act: 3.9111. Min Act: -0.0000

Data Index: 1156025 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7470. Min Act: -0.0000

Data Index: 37679 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.2924. Min Act: -0.0000

Data Index: 17340 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.2653. Min Act: -0.0000

Data Index: 252547 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.1478. Min Act: -0.0000

Data Index: 1296955 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.0550. Min Act: -0.0000

Data Index: 210015 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.1453. Min Act: -0.0000

Data Index: 1251989 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.1265. Min Act: -0.0000

Data Index: 569807 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.1032. Min Act: -0.0000

Data Index: 285304 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.8811. Min Act: -0.0000

Data Index: 200915 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.8730. Min Act: -0.0000

Data Index: 99681 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.9907. Min Act: -0.0000

Data Index: 8989 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.8186. Min Act: -0.0000

Data Index: 414971 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.8052. Min Act: -0.0000

Data Index: 1340549 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.7617. Min Act: -0.0000

Data Index: 518232 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.7547. Min Act: -0.0000

Data Index: 261849 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.7443. Min Act: -0.0000

Data Index: 709696 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.8788. Min Act: -0.0000

Data Index: 858246 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.5949. Min Act: -0.0000

Data Index: 1234534 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 3.9111. Min Range: -3.9111

Max Act: 2.7207. Min Act: -0.0000

Data Index: 40479 (C4 (Web Text))

Max Activating Token Index: 106