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

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

Neuron 4761 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: 7.7868. Min Range: -7.7868

Max Act: 7.7868. Min Act: -0.0000

Data Index: 1378747 (Python Code)

Max Activating Token Index: 973

Text #1

Max Range: 7.7868. Min Range: -7.7868

Max Act: 7.4764. Min Act: -0.0000

Data Index: 1283893 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 7.7868. Min Range: -7.7868

Max Act: 7.4407. Min Act: -0.0000

Data Index: 948703 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 7.7868. Min Range: -7.7868

Max Act: 7.4120. Min Act: -0.0000

Data Index: 267506 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 7.7868. Min Range: -7.7868

Max Act: 7.2906. Min Act: -0.0000

Data Index: 1596976 (Python Code)

Max Activating Token Index: 548

Text #5

Max Range: 7.7868. Min Range: -7.7868

Max Act: 7.4514. Min Act: -0.0000

Data Index: 1139854 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.7494. Min Act: -0.0000

Data Index: 1138847 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.8204. Min Act: -0.0000

Data Index: 400785 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.7827. Min Act: -0.0000

Data Index: 836899 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.7603. Min Act: -0.0000

Data Index: 1307089 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.8519. Min Act: -0.0000

Data Index: 844781 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.8624. Min Act: -0.0000

Data Index: 788842 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.6497. Min Act: -0.0000

Data Index: 860169 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.3737. Min Act: -0.0000

Data Index: 82126 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.4973. Min Act: -0.0000

Data Index: 571059 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.2532. Min Act: -0.0000

Data Index: 1160396 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.2833. Min Act: -0.0000

Data Index: 1116426 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.6394. Min Act: -0.0000

Data Index: 859370 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.1833. Min Act: -0.0000

Data Index: 307369 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 7.7868. Min Range: -7.7868

Max Act: 6.3449. Min Act: -0.0000

Data Index: 1101068 (C4 (Web Text))

Max Activating Token Index: 43