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

Dataset: The Pile

Neuron 4387 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: 0.2033. Min Range: -0.2033

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1997785 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1256535 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1340. Min Act: -0.0000

Data Index: 678764 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1292. Min Act: -0.0000

Data Index: 504235 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1161. Min Act: -0.0000

Data Index: 642596 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1797107 (The Pile)

Max Activating Token Index: 597

Text #6

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1166. Min Act: -0.0000

Data Index: 333507 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1322908 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1873978 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1134. Min Act: -0.0000

Data Index: 192131 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1055. Min Act: -0.0000

Data Index: 875778 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1149618 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.0989. Min Act: -0.0000

Data Index: 292440 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1364427 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1408006 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1263665 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1002. Min Act: -0.0000

Data Index: 590115 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1020. Min Act: -0.0000

Data Index: 218074 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.0971. Min Act: -0.0000

Data Index: 513151 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1990478 (The Pile)

Max Activating Token Index: 988