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

Dataset: The Pile

Neuron 1141 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.7687. Min Act: -0.0000

Data Index: 829229 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.8658. Min Act: -0.0000

Data Index: 373979 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.8790. Min Act: -0.0000

Data Index: 1239160 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.7800. Min Act: -0.0000

Data Index: 580112 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.7659. Min Act: -0.0000

Data Index: 1144525 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.7629. Min Act: -0.0000

Data Index: 613406 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.7031. Min Act: -0.0000

Data Index: 1267614 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.7321. Min Act: -0.0000

Data Index: 390547 (The Pile)

Max Activating Token Index: 342

Text #8

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1726322 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1960835 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.7411. Min Act: -0.0000

Data Index: 701154 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.6418. Min Act: -0.0000

Data Index: 529596 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.5895. Min Act: -0.0000

Data Index: 622954 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.6258. Min Act: -0.0000

Data Index: 1607683 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1890830 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1568256 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.5819. Min Act: -0.0000

Data Index: 383318 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1906897 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.4796. Min Act: -0.0000

Data Index: 355204 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 1.8790. Min Range: -1.8790

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1802828 (The Pile)

Max Activating Token Index: 852