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

Dataset: The Pile

Neuron 292 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: 0.4630. Min Range: -0.4630

Max Act: 0.4574. Min Act: -0.0000

Data Index: 741145 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1040089 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.4433. Min Act: -0.0000

Data Index: 616062 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.4128. Min Act: -0.0000

Data Index: 895828 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1110692 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.4078. Min Act: -0.0000

Data Index: 514463 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3931. Min Act: -0.0000

Data Index: 519894 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1515506 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1614813 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1384195 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1683170 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3851. Min Act: -0.0000

Data Index: 615257 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1308891 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1823604 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3834. Min Act: -0.0000

Data Index: 592931 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3777. Min Act: -0.0000

Data Index: 548166 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1328888 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3765. Min Act: -0.0000

Data Index: 468006 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3601. Min Act: -0.0000

Data Index: 651304 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1803799 (The Pile)

Max Activating Token Index: 710