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

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

Neuron 4322 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.9614. Min Act: -0.0000

Data Index: 94016 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.7522. Min Act: -0.0000

Data Index: 3623 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.7306. Min Act: -0.0000

Data Index: 876361 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.7108. Min Act: -0.0000

Data Index: 462052 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1303015 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6485. Min Act: -0.0000

Data Index: 789579 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1081695 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5406. Min Act: -0.0000

Data Index: 731107 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5738. Min Act: 0.0000

Data Index: 811015 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5622. Min Act: 0.0000

Data Index: 594817 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5552. Min Act: -0.0000

Data Index: 378670 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1016931 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1016849 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1053911 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1521955 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1458764 (Python Code)

Max Activating Token Index: 421

Text #16

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1025533 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1459089 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5281. Min Act: -0.0000

Data Index: 908018 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.5619. Min Act: -0.0000

Data Index: 186903 (C4 (Web Text))

Max Activating Token Index: 810