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

Dataset: The Pile

Neuron 4037 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: 1.6559. Min Range: -1.6559

Max Act: 1.6559. Min Act: -0.0000

Data Index: 524179 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4958. Min Act: -0.0000

Data Index: 767558 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4448. Min Act: -0.0000

Data Index: 678788 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3336. Min Act: -0.0000

Data Index: 357993 (The Pile)

Max Activating Token Index: 295

Text #4

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3956. Min Act: -0.0000

Data Index: 403664 (The Pile)

Max Activating Token Index: 721

Text #5

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3287. Min Act: -0.0000

Data Index: 838797 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3628. Min Act: -0.0000

Data Index: 255084 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1411087 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.1945. Min Act: -0.0000

Data Index: 764643 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2989. Min Act: -0.0000

Data Index: 842197 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2338. Min Act: -0.0000

Data Index: 101672 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1115797 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1198454 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2880. Min Act: -0.0000

Data Index: 792893 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2243. Min Act: -0.0000

Data Index: 890230 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2916. Min Act: -0.0000

Data Index: 545665 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2608. Min Act: -0.0000

Data Index: 917632 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2915. Min Act: -0.0000

Data Index: 461586 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.2349. Min Act: -0.0000

Data Index: 629004 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1931158 (The Pile)

Max Activating Token Index: 778