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

Dataset: The Pile

Neuron 4522 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1341. Min Range: -1.1341

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1155709 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1878951 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1854134 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6549. Min Act: -0.0000

Data Index: 636246 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6451. Min Act: -0.0000

Data Index: 553712 (The Pile)

Max Activating Token Index: 546

Text #5

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1042774 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1983718 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1128008 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6031. Min Act: -0.0000

Data Index: 451042 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1917715 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5954. Min Act: -0.0000

Data Index: 785907 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1122366 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1907047 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5605. Min Act: -0.0000

Data Index: 159460 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5113. Min Act: -0.0000

Data Index: 485555 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1267551 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.4905. Min Act: -0.0000

Data Index: 79122 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1619667 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1210426 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1805804 (The Pile)

Max Activating Token Index: 789