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

Dataset: The Pile

Neuron 3618 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: 0.7625. Min Range: -0.7625

Max Act: 0.7625. Min Act: -0.0000

Data Index: 18958 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4848. Min Act: -0.0000

Data Index: 774831 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1612548 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.5197. Min Act: -0.0000

Data Index: 380011 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.5108. Min Act: -0.0000

Data Index: 412136 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4658. Min Act: -0.0000

Data Index: 465605 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1400533 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1642448 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1913500 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1788174 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4363. Min Act: -0.0000

Data Index: 153220 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.3968. Min Act: -0.0000

Data Index: 368867 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1945746 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.4253. Min Act: -0.0000

Data Index: 706319 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1107209 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1981723 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1466855 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.3670. Min Act: -0.0000

Data Index: 290757 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1257293 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 0.7625. Min Range: -0.7625

Max Act: 0.3785. Min Act: -0.0000

Data Index: 794504 (The Pile)

Max Activating Token Index: 627