Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3273 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1225. Min Act: -0.0000

Data Index: 887006 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1500633 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0917. Min Act: 0.0000

Data Index: 262705 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1394611 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1021. Min Act: -0.0000

Data Index: 838149 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1100. Min Act: -0.0000

Data Index: 171959 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1886121 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1138167 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0999. Min Act: -0.0000

Data Index: 577731 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0989. Min Act: 0.0000

Data Index: 1845267 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1139031 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0961. Min Act: 0.0000

Data Index: 230938 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1227136 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0923. Min Act: 0.0000

Data Index: 1780779 (The Pile)

Max Activating Token Index: 697

Text #14

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1011. Min Act: -0.0000

Data Index: 133504 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1901442 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1230541 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0866. Min Act: -0.0000

Data Index: 623326 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1662204 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0916. Min Act: 0.0000

Data Index: 427170 (The Pile)

Max Activating Token Index: 907