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

Dataset: The Pile

Neuron 3940 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: 0.5335. Min Range: -0.5335

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1859198 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4841. Min Act: -0.0000

Data Index: 154791 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4118. Min Act: -0.0000

Data Index: 376511 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3749. Min Act: -0.0000

Data Index: 671995 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3344. Min Act: -0.0000

Data Index: 267520 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3613. Min Act: -0.0000

Data Index: 486240 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1987138 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3128. Min Act: -0.0000

Data Index: 441106 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2936. Min Act: -0.0000

Data Index: 617456 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1198616 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1003511 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1921653 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2817. Min Act: -0.0000

Data Index: 985856 (The Pile)

Max Activating Token Index: 671

Text #13

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2899. Min Act: -0.0000

Data Index: 33411 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2776. Min Act: -0.0000

Data Index: 787008 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2827. Min Act: -0.0000

Data Index: 710393 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2602. Min Act: -0.0000

Data Index: 851325 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2900. Min Act: -0.0000

Data Index: 576310 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2779. Min Act: -0.0000

Data Index: 728980 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1779848 (The Pile)

Max Activating Token Index: 555