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

Dataset: The Pile

Neuron 1370 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: 1.3611. Min Range: -1.3611

Max Act: 1.3611. Min Act: -0.0000

Data Index: 405269 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 1.3611. Min Range: -1.3611

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1342432 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 1.3611. Min Range: -1.3611

Max Act: 1.0034. Min Act: -0.0000

Data Index: 436599 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.9714. Min Act: -0.0000

Data Index: 399272 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.9516. Min Act: -0.0000

Data Index: 504838 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1655708 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1923146 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1818587 (The Pile)

Max Activating Token Index: 799

Text #8

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8366. Min Act: -0.0000

Data Index: 740757 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1541677 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8441. Min Act: -0.0000

Data Index: 153522 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8052. Min Act: -0.0000

Data Index: 643084 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1051380 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8277. Min Act: -0.0000

Data Index: 258687 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8236. Min Act: -0.0000

Data Index: 619523 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1855606 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.7845. Min Act: -0.0000

Data Index: 183989 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8609. Min Act: -0.0000

Data Index: 1819188 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1609868 (The Pile)

Max Activating Token Index: 973

Text #19

Max Range: 1.3611. Min Range: -1.3611

Max Act: 0.8225. Min Act: -0.0000

Data Index: 741862 (The Pile)

Max Activating Token Index: 508