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

Dataset: The Pile

Neuron 3782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.7015. Min Act: -0.0000

Data Index: 509091 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1970657 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1239361 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6138. Min Act: -0.0000

Data Index: 772657 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1963022 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6490. Min Act: -0.0000

Data Index: 866954 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1606870 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6268. Min Act: -0.0000

Data Index: 81936 (The Pile)

Max Activating Token Index: 585

Text #8

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1413224 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5943. Min Act: -0.0000

Data Index: 220315 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1525293 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1009871 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1998919 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.6047. Min Act: -0.0000

Data Index: 34222 (The Pile)

Max Activating Token Index: 470

Text #14

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5767. Min Act: -0.0000

Data Index: 243932 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1294168 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5922. Min Act: -0.0000

Data Index: 686482 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5862. Min Act: -0.0000

Data Index: 97473 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1800004 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1832822 (The Pile)

Max Activating Token Index: 737