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

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

Neuron 1533 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8666. Min Act: -0.0000

Data Index: 1517975 (Python Code)

Max Activating Token Index: 628

Text #1

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.8602. Min Act: -0.0000

Data Index: 1105221 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.5271. Min Act: -0.0000

Data Index: 493778 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.5411. Min Act: -0.0000

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.4565. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.4378. Min Act: -0.0000

Data Index: 1120936 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.5577. Min Act: -0.0000

Data Index: 1450736 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.3721. Min Act: -0.0000

Data Index: 529457 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1568860 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.3299. Min Act: -0.0000

Data Index: 232545 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.3500. Min Act: -0.0000

Data Index: 814980 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.3876. Min Act: -0.0000

Data Index: 459339 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1257744 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.4124. Min Act: -0.0000

Data Index: 1181273 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.2949. Min Act: -0.0000

Data Index: 101032 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1570417 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.3429. Min Act: -0.0000

Data Index: 248487 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.4757. Min Act: -0.0000

Data Index: 636813 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1224908 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.8666. Min Range: -1.8666

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1027530 (C4 (Web Text))

Max Activating Token Index: 148