Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1405 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1744008 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5658. Min Act: -0.0000

Data Index: 411121 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1009470 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1803591 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4895. Min Act: -0.0000

Data Index: 817805 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1436174 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1163758 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1907890 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4320. Min Act: -0.0000

Data Index: 93309 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4656. Min Act: -0.0000

Data Index: 11516 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4222. Min Act: -0.0000

Data Index: 516713 (The Pile)

Max Activating Token Index: 915

Text #11

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1737103 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1446533 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1132687 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1857036 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1692921 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4671. Min Act: -0.0000

Data Index: 574607 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.4223. Min Act: -0.0000

Data Index: 304829 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1527229 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.6108. Min Range: -0.6108

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1687064 (The Pile)

Max Activating Token Index: 549