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

Dataset: The Pile

Neuron 756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1462804 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1916078 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1050264 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4906. Min Act: -0.0000

Data Index: 734880 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5785. Min Act: -0.0000

Data Index: 245049 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5387. Min Act: -0.0000

Data Index: 99978 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1122986 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1865559 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4813. Min Act: -0.0000

Data Index: 47612 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4399. Min Act: -0.0000

Data Index: 711175 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.3895. Min Act: -0.0000

Data Index: 135742 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1627599 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4189. Min Act: -0.0000

Data Index: 113135 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1987194 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4860. Min Act: -0.0000

Data Index: 410679 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1279145 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1491207 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.3848. Min Act: -0.0000

Data Index: 366202 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1765300 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4761. Min Act: -0.0000

Data Index: 299524 (The Pile)

Max Activating Token Index: 977