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

Dataset: The Pile

Neuron 1047 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: 0.7522. Min Range: -0.7522

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1752923 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1404753 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1945292 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7063. Min Act: -0.0000

Data Index: 729840 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1443166 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1865244 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6486. Min Act: -0.0000

Data Index: 790675 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6466. Min Act: -0.0000

Data Index: 142729 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6527. Min Act: 0.0000

Data Index: 496112 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1252850 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5744. Min Act: -0.0000

Data Index: 387061 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1590856 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5607. Min Act: -0.0000

Data Index: 54913 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5308. Min Act: -0.0000

Data Index: 818192 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5344. Min Act: -0.0000

Data Index: 98619 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1174981 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1610143 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1110320 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1320258 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5415. Min Act: -0.0000

Data Index: 488221 (The Pile)

Max Activating Token Index: 752