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

Dataset: The Pile

Neuron 4534 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7805. Min Act: -0.0000

Data Index: 240371 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6820. Min Act: -0.0000

Data Index: 748089 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1956731 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1511881 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5437. Min Act: -0.0000

Data Index: 493661 (The Pile)

Max Activating Token Index: 131

Text #5

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5470. Min Act: -0.0000

Data Index: 420594 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5273. Min Act: -0.0000

Data Index: 817866 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5279. Min Act: -0.0000

Data Index: 911670 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5706. Min Act: -0.0000

Data Index: 227251 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1559785 (The Pile)

Max Activating Token Index: 451

Text #10

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4900. Min Act: -0.0000

Data Index: 717186 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5296. Min Act: -0.0000

Data Index: 790253 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1353352 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1207209 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4862. Min Act: -0.0000

Data Index: 433325 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4263. Min Act: -0.0000

Data Index: 226051 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1180707 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1356397 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1891714 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.4650. Min Act: -0.0000

Data Index: 630116 (The Pile)

Max Activating Token Index: 40