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

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

Neuron 5340 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: 1.6695. Min Range: -1.6695

Max Act: 1.6695. Min Act: -0.0000

Data Index: 1165826 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.6404. Min Act: -0.0000

Data Index: 318576 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.5210. Min Act: -0.0000

Data Index: 685158 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.5501. Min Act: -0.0000

Data Index: 855727 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1643595 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1263612 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.3873. Min Act: -0.0000

Data Index: 805882 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.3713. Min Act: -0.0000

Data Index: 751020 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1133747 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.3374. Min Act: -0.0000

Data Index: 490244 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.3017. Min Act: -0.0000

Data Index: 680469 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1120493 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.1960. Min Act: -0.0000

Data Index: 1087374 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.2497. Min Act: -0.0000

Data Index: 773058 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.3882. Min Act: -0.0000

Data Index: 82072 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.2157. Min Act: -0.0000

Data Index: 383458 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1319247 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.2109. Min Act: -0.0000

Data Index: 781265 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.2090. Min Act: -0.0000

Data Index: 329582 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.6695. Min Range: -1.6695

Max Act: 1.1998. Min Act: -0.0000

Data Index: 720696 (C4 (Web Text))

Max Activating Token Index: 191