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

Dataset: The Pile

Neuron 5104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6540. Min Act: -0.0000

Data Index: 252918 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1995430 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5673. Min Act: -0.0000

Data Index: 138756 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1905002 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1389999 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4861. Min Act: -0.0000

Data Index: 636571 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1021448 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1933352 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4708. Min Act: -0.0000

Data Index: 861159 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4516. Min Act: -0.0000

Data Index: 232209 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4603. Min Act: -0.0000

Data Index: 453511 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1999566 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4528. Min Act: -0.0000

Data Index: 541342 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1478058 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1961995 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4719. Min Act: -0.0000

Data Index: 369323 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1698728 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1659358 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1903813 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1354467 (The Pile)

Max Activating Token Index: 759