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

Dataset: The Pile

Neuron 4320 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: 0.1233. Min Range: -0.1233

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1204590 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1204. Min Act: -0.0000

Data Index: 476203 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1184. Min Act: -0.0000

Data Index: 211497 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1645498 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1190. Min Act: -0.0000

Data Index: 919812 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1983872 (The Pile)

Max Activating Token Index: 325

Text #6

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1081. Min Act: -0.0000

Data Index: 442832 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1605987 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1657999 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1161298 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1989251 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1891303 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1084974 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1370609 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0978. Min Act: -0.0000

Data Index: 461246 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0999. Min Act: -0.0000

Data Index: 151202 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1667345 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1251315 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0945. Min Act: -0.0000

Data Index: 838129 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0946. Min Act: -0.0000

Data Index: 73198 (The Pile)

Max Activating Token Index: 209