Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 592 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.7904. Min Act: -0.0000

Data Index: 1767550 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.4520. Min Act: -0.0000

Data Index: 1353000 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.2267. Min Act: -0.0000

Data Index: 1141724 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.3726. Min Act: -0.0000

Data Index: 546892 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.3609. Min Act: -0.0000

Data Index: 288621 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.2036. Min Act: -0.0000

Data Index: 1186400 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.1989. Min Act: -0.0000

Data Index: 408226 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.4686. Min Act: -0.0000

Data Index: 889082 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.4818. Min Act: -0.0000

Data Index: 925843 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.3429. Min Act: -0.0000

Data Index: 1212428 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.2671. Min Act: -0.0000

Data Index: 1104179 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.2636. Min Act: -0.0000

Data Index: 1057934 (The Pile)

Max Activating Token Index: 656

Text #12

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.3756. Min Act: -0.0000

Data Index: 674377 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.2092. Min Act: -0.0000

Data Index: 279206 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.0608. Min Act: -0.0000

Data Index: 1163537 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.0606. Min Act: -0.0000

Data Index: 1727657 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.0017. Min Act: -0.0000

Data Index: 1724080 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 3.7904. Min Range: -3.7904

Max Act: 2.9929. Min Act: -0.0000

Data Index: 391040 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 3.7904. Min Range: -3.7904

Max Act: 3.1043. Min Act: -0.0000

Data Index: 621061 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 3.7904. Min Range: -3.7904

Max Act: 2.9851. Min Act: -0.0000

Data Index: 714523 (The Pile)

Max Activating Token Index: 129