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

Dataset: The Pile

Neuron 2540 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.6138. Min Act: -0.0000

Data Index: 168043 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5546. Min Act: -0.0000

Data Index: 240747 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5588. Min Act: -0.0000

Data Index: 757343 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1297404 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1823176 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4500. Min Act: -0.0000

Data Index: 971367 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4690. Min Act: -0.0000

Data Index: 930626 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1963981 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1145289 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1173558 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3973. Min Act: -0.0000

Data Index: 37858 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1556538 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1713227 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1699506 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1070309 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1573674 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1483731 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1059564 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4165. Min Act: -0.0000

Data Index: 374143 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1379766 (The Pile)

Max Activating Token Index: 513