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

Dataset: The Pile

Neuron 4030 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: 0.9689. Min Range: -0.9689

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1435115 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1189122 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1810881 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5715. Min Act: -0.0000

Data Index: 563270 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6102. Min Act: -0.0000

Data Index: 720785 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6109. Min Act: -0.0000

Data Index: 95139 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5590. Min Act: -0.0000

Data Index: 40777 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5322. Min Act: -0.0000

Data Index: 411689 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5246. Min Act: -0.0000

Data Index: 749658 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5200. Min Act: -0.0000

Data Index: 88224 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1317897 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1713724 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5138. Min Act: -0.0000

Data Index: 377356 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5199. Min Act: -0.0000

Data Index: 420511 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1552783 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.4792. Min Act: -0.0000

Data Index: 414082 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5284. Min Act: -0.0000

Data Index: 325714 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1693253 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1523677 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.4935. Min Act: -0.0000

Data Index: 690887 (The Pile)

Max Activating Token Index: 78