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

Dataset: The Pile

Neuron 1172 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: 0.8808. Min Range: -0.8808

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1942620 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1100177 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7056. Min Act: -0.0000

Data Index: 524136 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1022196 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1751299 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6907. Min Act: -0.0000

Data Index: 351459 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1028045 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1747408 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1985974 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6733. Min Act: -0.0000

Data Index: 804434 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1167901 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1608984 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5854. Min Act: -0.0000

Data Index: 391051 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1427076 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5890. Min Act: -0.0000

Data Index: 75965 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1928435 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5525. Min Act: -0.0000

Data Index: 568301 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1551688 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5839. Min Act: -0.0000

Data Index: 925593 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5682. Min Act: -0.0000

Data Index: 882251 (The Pile)

Max Activating Token Index: 122