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

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

Neuron 1405 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: 1.2682. Min Range: -1.2682

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1011461 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.9208. Min Act: -0.0000

Data Index: 774132 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1518602 (Python Code)

Max Activating Token Index: 169

Text #3

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1390250 (Python Code)

Max Activating Token Index: 479

Text #4

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.7166. Min Act: -0.0000

Data Index: 510887 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1637916 (Python Code)

Max Activating Token Index: 625

Text #6

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1303690 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.7171. Min Act: -0.0000

Data Index: 904081 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6856. Min Act: -0.0000

Data Index: 849389 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1397181 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1477077 (Python Code)

Max Activating Token Index: 795

Text #11

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1487439 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6603. Min Act: -0.0000

Data Index: 430417 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1572793 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1171030 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1494457 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6360. Min Act: -0.0000

Data Index: 834912 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1651483 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1401812 (Python Code)

Max Activating Token Index: 533

Text #19

Max Range: 1.2682. Min Range: -1.2682

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1473133 (Python Code)

Max Activating Token Index: 758