Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1958 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.9026. Min Act: -0.0000

Data Index: 313367 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1428181 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7197. Min Act: -0.0000

Data Index: 386978 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6394. Min Act: -0.0000

Data Index: 81466 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6823. Min Act: -0.0000

Data Index: 696631 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1177265 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6555. Min Act: -0.0000

Data Index: 635012 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1400169 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1900764 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1028739 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.5680. Min Act: -0.0000

Data Index: 767243 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1383557 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1206637 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.5810. Min Act: -0.0000

Data Index: 164016 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.5982. Min Act: -0.0000

Data Index: 739456 (The Pile)

Max Activating Token Index: 490

Text #15

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1459567 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1703993 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1894686 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.5832. Min Act: -0.0000

Data Index: 640096 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 0.9026. Min Range: -0.9026

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1586368 (The Pile)

Max Activating Token Index: 138