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

Dataset: The Pile

Neuron 1557 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.5062. Min Act: -0.0000

Data Index: 501458 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1228873 (The Pile)

Max Activating Token Index: 849

Text #2

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4085. Min Act: -0.0000

Data Index: 353617 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4166. Min Act: -0.0000

Data Index: 643240 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4395. Min Act: -0.0000

Data Index: 189707 (The Pile)

Max Activating Token Index: 979

Text #5

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1233018 (The Pile)

Max Activating Token Index: 855

Text #6

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4033. Min Act: -0.0000

Data Index: 33840 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1695042 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1495139 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1249000 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1092989 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4087. Min Act: -0.0000

Data Index: 691110 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1572734 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1859746 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3785. Min Act: -0.0000

Data Index: 390522 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1587274 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3709. Min Act: -0.0000

Data Index: 432549 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1132801 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3874. Min Act: -0.0000

Data Index: 962271 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3594. Min Act: -0.0000

Data Index: 378310 (The Pile)

Max Activating Token Index: 184