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

Dataset: The Pile

Neuron 3428 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1231001 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1326701 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1172. Min Act: -0.0000

Data Index: 442952 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1476915 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1082. Min Act: -0.0000

Data Index: 595049 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0988. Min Act: -0.0000

Data Index: 748240 (The Pile)

Max Activating Token Index: 74

Text #6

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1097. Min Act: -0.0000

Data Index: 875418 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1822186 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1007. Min Act: -0.0000

Data Index: 631712 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1076. Min Act: -0.0000

Data Index: 325517 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1263048 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1175877 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1810854 (The Pile)

Max Activating Token Index: 503

Text #13

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1301856 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1102. Min Act: -0.0000

Data Index: 690023 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1474659 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1724008 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0936. Min Act: -0.0000

Data Index: 567686 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1571121 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1765308 (The Pile)

Max Activating Token Index: 442