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

Dataset: The Pile

Neuron 2536 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: 0.6318. Min Range: -0.6318

Max Act: 0.6318. Min Act: -0.0000

Data Index: 567349 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5712. Min Act: -0.0000

Data Index: 627952 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1472149 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4939. Min Act: -0.0000

Data Index: 603118 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5208. Min Act: -0.0000

Data Index: 330283 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5114. Min Act: -0.0000

Data Index: 407134 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4786. Min Act: -0.0000

Data Index: 282912 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4622. Min Act: -0.0000

Data Index: 342776 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1542653 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1927589 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4503. Min Act: -0.0000

Data Index: 309446 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1670465 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1472913 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4258. Min Act: -0.0000

Data Index: 595179 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1612379 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1281248 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1233093 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4617. Min Act: -0.0000

Data Index: 688072 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4125. Min Act: -0.0000

Data Index: 251472 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4318. Min Act: -0.0000

Data Index: 161480 (The Pile)

Max Activating Token Index: 14