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

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

Neuron 1258 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.7070. Min Act: -0.0000

Data Index: 311412 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1337815 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6880. Min Act: -0.0000

Data Index: 400671 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6566. Min Act: -0.0000

Data Index: 832357 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6575. Min Act: -0.0000

Data Index: 397950 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1195754 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1264480 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1189969 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6331. Min Act: -0.0000

Data Index: 66396 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1223034 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5670. Min Act: -0.0000

Data Index: 829817 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5982. Min Act: -0.0000

Data Index: 167752 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6257. Min Act: -0.0000

Data Index: 167900 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5715. Min Act: -0.0000

Data Index: 811806 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6196. Min Act: -0.0000

Data Index: 160835 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5614. Min Act: -0.0000

Data Index: 958336 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5614. Min Act: -0.0000

Data Index: 122966 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5457. Min Act: -0.0000

Data Index: 487189 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5588. Min Act: -0.0000

Data Index: 227160 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5780. Min Act: -0.0000

Data Index: 197065 (C4 (Web Text))

Max Activating Token Index: 992