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

Dataset: The Pile

Neuron 592 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2897. Min Act: -0.0000

Data Index: 401455 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1406. Min Act: -0.0000

Data Index: 447510 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1038689 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0529. Min Act: -0.0000

Data Index: 72138 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0904. Min Act: -0.0000

Data Index: 976133 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1276417 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9558. Min Act: -0.0000

Data Index: 106943 (The Pile)

Max Activating Token Index: 963

Text #7

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8653. Min Act: -0.0000

Data Index: 336060 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9102. Min Act: -0.0000

Data Index: 980233 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1982119 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9678. Min Act: -0.0000

Data Index: 695822 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8293. Min Act: -0.0000

Data Index: 114859 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9110. Min Act: -0.0000

Data Index: 313036 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9469. Min Act: -0.0000

Data Index: 700204 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0022. Min Act: -0.0000

Data Index: 714946 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1542407 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9843. Min Act: -0.0000

Data Index: 151410 (The Pile)

Max Activating Token Index: 699

Text #17

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1690552 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1991754 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9718. Min Act: -0.0000

Data Index: 13385 (The Pile)

Max Activating Token Index: 1012