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

Dataset: The Pile

Neuron 4060 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: 1.3092. Min Range: -1.3092

Max Act: 1.3092. Min Act: -0.0000

Data Index: 422455 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1476674 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1504. Min Act: -0.0000

Data Index: 111474 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1548262 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1075. Min Act: -0.0000

Data Index: 784512 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1412145 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0116. Min Act: -0.0000

Data Index: 878738 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0403. Min Act: -0.0000

Data Index: 1790219 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9432. Min Act: -0.0000

Data Index: 505840 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1171139 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9790. Min Act: -0.0000

Data Index: 950952 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9204. Min Act: -0.0000

Data Index: 119381 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9082. Min Act: -0.0000

Data Index: 934092 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9095. Min Act: -0.0000

Data Index: 503578 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8861. Min Act: -0.0000

Data Index: 349284 (The Pile)

Max Activating Token Index: 170

Text #15

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8856. Min Act: -0.0000

Data Index: 408196 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9395. Min Act: -0.0000

Data Index: 887784 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1786234 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8603. Min Act: -0.0000

Data Index: 451788 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.8287. Min Act: -0.0000

Data Index: 830607 (The Pile)

Max Activating Token Index: 517