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

Dataset: The Pile

Neuron 1888 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: 1.5871. Min Range: -1.5871

Max Act: 1.5871. Min Act: -0.0000

Data Index: 1858518 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.4107. Min Act: -0.0000

Data Index: 183817 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.5163. Min Act: -0.0000

Data Index: 991197 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.1244. Min Act: -0.0000

Data Index: 389856 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.1074. Min Act: -0.0000

Data Index: 694960 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 1.5871. Min Range: -1.5871

Max Act: 0.9921. Min Act: -0.0000

Data Index: 139232 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1103606 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1179611 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1887462 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.0678. Min Act: -0.0000

Data Index: 61602 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.0688. Min Act: -0.0000

Data Index: 409335 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.0246. Min Act: -0.0000

Data Index: 952254 (The Pile)

Max Activating Token Index: 649

Text #12

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1053155 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.0227. Min Act: -0.0000

Data Index: 1335414 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 1.5871. Min Range: -1.5871

Max Act: 0.9497. Min Act: -0.0000

Data Index: 919651 (The Pile)

Max Activating Token Index: 795

Text #15

Max Range: 1.5871. Min Range: -1.5871

Max Act: 0.9850. Min Act: -0.0000

Data Index: 215918 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 1.5871. Min Range: -1.5871

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1167814 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 1.5871. Min Range: -1.5871

Max Act: 0.9015. Min Act: -0.0000

Data Index: 989340 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 1.5871. Min Range: -1.5871

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1480214 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 1.5871. Min Range: -1.5871

Max Act: 0.9417. Min Act: -0.0000

Data Index: 53106 (The Pile)

Max Activating Token Index: 185