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

Dataset: The Pile

Neuron 3107 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: 1.2239. Min Range: -1.2239

Max Act: 1.0903. Min Act: -0.0000

Data Index: 834607 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 1.2239. Min Range: -1.2239

Max Act: 1.2239. Min Act: -0.0000

Data Index: 1571228 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 1.2239. Min Range: -1.2239

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1890187 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 1.2239. Min Range: -1.2239

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1216993 (The Pile)

Max Activating Token Index: 230

Text #4

Max Range: 1.2239. Min Range: -1.2239

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1378865 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 1.2239. Min Range: -1.2239

Max Act: 1.0379. Min Act: -0.0000

Data Index: 559344 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 1.2239. Min Range: -1.2239

Max Act: 1.0108. Min Act: 0.0000

Data Index: 392251 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 1.2239. Min Range: -1.2239

Max Act: 1.0060. Min Act: -0.0000

Data Index: 920976 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9658. Min Act: 0.0000

Data Index: 922695 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1313155 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9836. Min Act: 0.0001

Data Index: 396118 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1687402 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 1.2239. Min Range: -1.2239

Max Act: 1.0060. Min Act: -0.0000

Data Index: 529413 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9798. Min Act: -0.0000

Data Index: 992772 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1012694 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1416585 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1455180 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9065. Min Act: -0.0000

Data Index: 260873 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9416. Min Act: -0.0000

Data Index: 671010 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 1.2239. Min Range: -1.2239

Max Act: 0.9899. Min Act: -0.0000

Data Index: 345689 (The Pile)

Max Activating Token Index: 470