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

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

Neuron 5646 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.3895. Min Act: -0.0000

Data Index: 677638 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.5390. Min Act: -0.0000

Data Index: 1457329 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1392216 (Python Code)

Max Activating Token Index: 659

Text #3

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.4223. Min Act: -0.0000

Data Index: 842466 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.4592. Min Act: -0.0000

Data Index: 232034 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.3707. Min Act: -0.0000

Data Index: 639247 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1638985 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.4166. Min Act: -0.0000

Data Index: 510393 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.1790. Min Act: -0.0000

Data Index: 1618060 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.2765. Min Act: -0.0000

Data Index: 279581 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1483349 (Python Code)

Max Activating Token Index: 766

Text #11

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1548956 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.1906. Min Act: -0.0000

Data Index: 619451 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1573498 (Python Code)

Max Activating Token Index: 852

Text #14

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1559397 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1473302 (Python Code)

Max Activating Token Index: 681

Text #16

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1565260 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1414835 (Python Code)

Max Activating Token Index: 137

Text #18

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1619244 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 1.5390. Min Range: -1.5390

Max Act: 1.1392. Min Act: -0.0000

Data Index: 778987 (C4 (Web Text))

Max Activating Token Index: 615