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

Dataset: The Pile

Neuron 3599 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: 1.0603. Min Range: -1.0603

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1272284 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 1.0603. Min Range: -1.0603

Max Act: 1.0603. Min Act: -0.0000

Data Index: 624236 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1039041 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9595. Min Act: -0.0000

Data Index: 841830 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1400135 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1188659 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8828. Min Act: -0.0000

Data Index: 841354 (The Pile)

Max Activating Token Index: 57

Text #7

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1595186 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9247. Min Act: -0.0000

Data Index: 74774 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1983468 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1542926 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8818. Min Act: -0.0000

Data Index: 659627 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1613721 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1593998 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8474. Min Act: -0.0000

Data Index: 510824 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1426355 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7537. Min Act: -0.0000

Data Index: 136338 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1579719 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1645439 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 1.0603. Min Range: -1.0603

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1362885 (The Pile)

Max Activating Token Index: 155