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

Dataset: The Pile

Neuron 605 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: 0.1130. Min Range: -0.1130

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1183262 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1735470 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1088. Min Act: -0.0000

Data Index: 360677 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1249925 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0998. Min Act: -0.0000

Data Index: 111004 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1016. Min Act: -0.0000

Data Index: 469459 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0965. Min Act: -0.0000

Data Index: 362433 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0894. Min Act: -0.0000

Data Index: 940182 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1787790 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0897. Min Act: -0.0000

Data Index: 874938 (The Pile)

Max Activating Token Index: 61

Text #10

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1943124 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0885. Min Act: -0.0000

Data Index: 461087 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0660. Min Act: -0.0000

Data Index: 334989 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0814. Min Act: -0.0000

Data Index: 369250 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0880. Min Act: -0.0000

Data Index: 341293 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0868. Min Act: -0.0000

Data Index: 890039 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0832. Min Act: -0.0000

Data Index: 963352 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1397126 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1852577 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1193451 (The Pile)

Max Activating Token Index: 891