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

Dataset: The Pile

Neuron 723 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: 0.2869. Min Range: -0.2869

Max Act: 0.2869. Min Act: -0.0000

Data Index: 103947 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1114947 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2788. Min Act: -0.0000

Data Index: 25722 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2714. Min Act: -0.0000

Data Index: 219270 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2665. Min Act: -0.0000

Data Index: 474403 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2388. Min Act: -0.0000

Data Index: 756896 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2708. Min Act: -0.0000

Data Index: 668180 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2664. Min Act: -0.0000

Data Index: 26166 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2434. Min Act: -0.0000

Data Index: 430490 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1199124 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2657. Min Act: -0.0000

Data Index: 710341 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1097445 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2376. Min Act: -0.0000

Data Index: 431732 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1647658 (The Pile)

Max Activating Token Index: 241

Text #14

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2703. Min Act: -0.0000

Data Index: 989050 (The Pile)

Max Activating Token Index: 874

Text #15

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2575. Min Act: -0.0000

Data Index: 173392 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2565. Min Act: -0.0000

Data Index: 821776 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1301453 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2293. Min Act: -0.0000

Data Index: 764839 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2510. Min Act: -0.0000

Data Index: 548595 (The Pile)

Max Activating Token Index: 855