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

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

Neuron 364 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: 1.1463. Min Range: -1.1463

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1192089 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.0646. Min Act: -0.0000

Data Index: 420392 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8796. Min Act: -0.0000

Data Index: 431725 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1008410 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7802. Min Act: -0.0000

Data Index: 41342 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7852. Min Act: -0.0000

Data Index: 909102 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7042. Min Act: -0.0000

Data Index: 747533 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1452159 (Python Code)

Max Activating Token Index: 467

Text #8

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1256042 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1535895 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6871. Min Act: -0.0000

Data Index: 205732 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1629434 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6498. Min Act: -0.0000

Data Index: 468708 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1143470 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1473042 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.5727. Min Act: -0.0000

Data Index: 550840 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1363475 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.5843. Min Act: -0.0000

Data Index: 635932 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1246615 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.5868. Min Act: -0.0000

Data Index: 230769 (C4 (Web Text))

Max Activating Token Index: 113