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

Dataset: The Pile

Neuron 3405 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: 2.2779. Min Range: -2.2779

Max Act: 2.1840. Min Act: -0.0000

Data Index: 1706299 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.2779. Min Act: -0.0000

Data Index: 141441 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.0685. Min Act: -0.0000

Data Index: 628378 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.9337. Min Act: -0.0000

Data Index: 1573201 (The Pile)

Max Activating Token Index: 658

Text #4

Max Range: 2.2779. Min Range: -2.2779

Max Act: 2.0312. Min Act: -0.0000

Data Index: 511942 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.8417. Min Act: -0.0000

Data Index: 116570 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.9186. Min Act: -0.0000

Data Index: 1755962 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.7777. Min Act: -0.0000

Data Index: 368033 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.6911. Min Act: -0.0000

Data Index: 1931544 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.9004. Min Act: -0.0000

Data Index: 231114 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.6550. Min Act: -0.0000

Data Index: 423890 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1517646 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.7129. Min Act: -0.0000

Data Index: 1664002 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.6263. Min Act: -0.0000

Data Index: 965557 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.4410. Min Act: -0.0000

Data Index: 677040 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.5848. Min Act: -0.0000

Data Index: 1437956 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.6702. Min Act: -0.0000

Data Index: 981388 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.6508. Min Act: -0.0000

Data Index: 842715 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.6173. Min Act: -0.0000

Data Index: 613299 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 2.2779. Min Range: -2.2779

Max Act: 1.5306. Min Act: -0.0000

Data Index: 1964802 (The Pile)

Max Activating Token Index: 529