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

Dataset: The Pile

Neuron 788 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1201893 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7064. Min Act: -0.0000

Data Index: 719382 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.7084. Min Act: -0.0000

Data Index: 601635 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1798625 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6693. Min Act: -0.0000

Data Index: 531549 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6722. Min Act: -0.0000

Data Index: 688890 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1390241 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6311. Min Act: -0.0000

Data Index: 782072 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5669. Min Act: -0.0000

Data Index: 409841 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6202. Min Act: -0.0000

Data Index: 975365 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1611530 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.6270. Min Act: -0.0000

Data Index: 479031 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1873985 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5201. Min Act: -0.0000

Data Index: 820096 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5946. Min Act: -0.0000

Data Index: 227498 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5730. Min Act: -0.0000

Data Index: 178674 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5389. Min Act: -0.0000

Data Index: 704532 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1871243 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1874631 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 0.7401. Min Range: -0.7401

Max Act: 0.5525. Min Act: -0.0000

Data Index: 668009 (The Pile)

Max Activating Token Index: 259