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

Dataset: The Pile

Neuron 4646 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: 1.0741. Min Range: -1.0741

Max Act: 1.0741. Min Act: -0.0000

Data Index: 367840 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.8816. Min Act: -0.0000

Data Index: 783716 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1778012 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1177567 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.7679. Min Act: -0.0000

Data Index: 406827 (The Pile)

Max Activating Token Index: 764

Text #5

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1420743 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.8421. Min Act: -0.0000

Data Index: 204504 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1786253 (The Pile)

Max Activating Token Index: 866

Text #8

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.7258. Min Act: -0.0000

Data Index: 499596 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1873710 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1139436 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6653. Min Act: -0.0000

Data Index: 46894 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1216995 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1634399 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6590. Min Act: -0.0000

Data Index: 722385 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1435152 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1721905 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1001344 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6289. Min Act: -0.0000

Data Index: 912494 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 1.0741. Min Range: -1.0741

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1508857 (The Pile)

Max Activating Token Index: 479