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

Dataset: The Pile

Neuron 2802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5430. Min Act: -0.0000

Data Index: 381298 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1132863 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5657. Min Act: -0.0000

Data Index: 776563 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5679. Min Act: -0.0000

Data Index: 85880 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1775003 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1255767 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4908. Min Act: -0.0000

Data Index: 118940 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4841. Min Act: -0.0000

Data Index: 409044 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1783391 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5176. Min Act: -0.0000

Data Index: 748679 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1517198 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1632552 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4524. Min Act: -0.0000

Data Index: 174757 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1997849 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1975102 (The Pile)

Max Activating Token Index: 783

Text #15

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4578. Min Act: -0.0000

Data Index: 557180 (The Pile)

Max Activating Token Index: 979

Text #16

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4868. Min Act: -0.0000

Data Index: 347610 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.5011. Min Act: -0.0000

Data Index: 504851 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4497. Min Act: -0.0000

Data Index: 605454 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 0.5710. Min Range: -0.5710

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1170059 (The Pile)

Max Activating Token Index: 760