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

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

Neuron 3628 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.9915. Min Act: -0.0000

Data Index: 1411788 (Python Code)

Max Activating Token Index: 365

Text #1

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.7957. Min Act: -0.0000

Data Index: 1434916 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.8137. Min Act: -0.0000

Data Index: 1454730 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.6843. Min Act: -0.0000

Data Index: 1458264 (Python Code)

Max Activating Token Index: 962

Text #4

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1492605 (Python Code)

Max Activating Token Index: 806

Text #5

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.6378. Min Act: -0.0000

Data Index: 1391906 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.7245. Min Act: -0.0000

Data Index: 1475371 (Python Code)

Max Activating Token Index: 349

Text #7

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1422434 (Python Code)

Max Activating Token Index: 548

Text #8

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.6183. Min Act: -0.0000

Data Index: 1540430 (Python Code)

Max Activating Token Index: 438

Text #9

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1498550 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5550. Min Act: -0.0000

Data Index: 1417285 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1409731 (Python Code)

Max Activating Token Index: 753

Text #12

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1362450 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1577323 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1538661 (Python Code)

Max Activating Token Index: 628

Text #15

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1497441 (Python Code)

Max Activating Token Index: 961

Text #16

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.4575. Min Act: -0.0000

Data Index: 1594348 (Python Code)

Max Activating Token Index: 543

Text #17

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.3581. Min Act: -0.0000

Data Index: 1545506 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1642357 (Python Code)

Max Activating Token Index: 611

Text #19

Max Range: 1.9915. Min Range: -1.9915

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1368097 (Python Code)

Max Activating Token Index: 54