Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1383 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3873. Min Act: -0.0000

Data Index: 1006587 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.0978. Min Act: -0.0000

Data Index: 1628254 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.1758. Min Act: -0.0000

Data Index: 593435 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.1216. Min Act: -0.0000

Data Index: 371110 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.9133. Min Act: -0.0000

Data Index: 354648 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.8956. Min Act: -0.0000

Data Index: 1790503 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.0077. Min Act: -0.0000

Data Index: 1363264 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.1361. Min Act: -0.0000

Data Index: 183599 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.1716. Min Act: -0.0000

Data Index: 122213 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.6682. Min Act: -0.0000

Data Index: 505433 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2125. Min Act: -0.0000

Data Index: 899483 (The Pile)

Max Activating Token Index: 765

Text #11

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.7685. Min Act: -0.0000

Data Index: 1112519 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.7612. Min Act: -0.0000

Data Index: 1306428 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.6322. Min Act: -0.0000

Data Index: 475890 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.6188. Min Act: -0.0000

Data Index: 1716170 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.8620. Min Act: -0.0000

Data Index: 1578969 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.8592. Min Act: -0.0000

Data Index: 52514 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.4381. Min Act: -0.0000

Data Index: 882659 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.7024. Min Act: -0.0000

Data Index: 1206107 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 3.3873. Min Range: -3.3873

Max Act: 2.4318. Min Act: -0.0000

Data Index: 1501814 (The Pile)

Max Activating Token Index: 392