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

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

Neuron 4135 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4545. Min Range: -4.4545

Max Act: 4.4545. Min Act: -0.0000

Data Index: 1232884 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 4.4545. Min Range: -4.4545

Max Act: 3.0030. Min Act: -0.0000

Data Index: 1152161 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 4.4545. Min Range: -4.4545

Max Act: 2.8991. Min Act: -0.0000

Data Index: 1203296 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 4.4545. Min Range: -4.4545

Max Act: 2.4104. Min Act: -0.0000

Data Index: 227830 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 4.4545. Min Range: -4.4545

Max Act: 2.1044. Min Act: -0.0000

Data Index: 799706 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 4.4545. Min Range: -4.4545

Max Act: 2.0977. Min Act: -0.0000

Data Index: 957000 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 4.4545. Min Range: -4.4545

Max Act: 2.0552. Min Act: -0.0000

Data Index: 381810 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 4.4545. Min Range: -4.4545

Max Act: 2.0391. Min Act: -0.0001

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.9193. Min Act: -0.0000

Data Index: 1047021 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.9009. Min Act: -0.0000

Data Index: 356975 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.8461. Min Act: -0.0000

Data Index: 497023 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.6934. Min Act: -0.0000

Data Index: 197397 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.8477. Min Act: -0.0000

Data Index: 857511 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.8615. Min Act: -0.0000

Data Index: 65715 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.7461. Min Act: -0.0000

Data Index: 824699 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.8179. Min Act: -0.0000

Data Index: 923468 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.7724. Min Act: -0.0001

Data Index: 708283 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.7799. Min Act: -0.0000

Data Index: 22295 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.6129. Min Act: -0.0000

Data Index: 630826 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 4.4545. Min Range: -4.4545

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1088034 (C4 (Web Text))

Max Activating Token Index: 219