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

Dataset: The Pile

Neuron 1364 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: 0.0000

Data Index: 1486827 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1231195 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1045. Min Act: -0.0000

Data Index: 735312 (The Pile)

Max Activating Token Index: 3

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1890510 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1306391 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0994. Min Act: 0.0000

Data Index: 1932793 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0987. Min Act: -0.0000

Data Index: 716883 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0968. Min Act: -0.0000

Data Index: 168533 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1692967 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1035129 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0941. Min Act: -0.0000

Data Index: 754913 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0933. Min Act: -0.0000

Data Index: 19827 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1167598 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1917935 (The Pile)

Max Activating Token Index: 733

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1970859 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0899. Min Act: 0.0000

Data Index: 148405 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0889. Min Act: -0.0000

Data Index: 37928 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1289116 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0885. Min Act: 0.0000

Data Index: 1212769 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0901. Min Act: -0.0000

Data Index: 139266 (The Pile)

Max Activating Token Index: 349