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

Dataset: The Pile

Neuron 1174 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: 0.5848. Min Range: -0.5848

Max Act: 0.5848. Min Act: -0.0000

Data Index: 118874 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5057. Min Act: -0.0000

Data Index: 226867 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1263978 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1551563 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1145506 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5058. Min Act: -0.0000

Data Index: 663400 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4748. Min Act: -0.0000

Data Index: 401441 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4815. Min Act: -0.0000

Data Index: 960071 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4895. Min Act: -0.0000

Data Index: 763309 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4425. Min Act: -0.0000

Data Index: 920113 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4274. Min Act: -0.0000

Data Index: 276616 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1639272 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1792056 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1008787 (The Pile)

Max Activating Token Index: 31

Text #14

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1161772 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1089871 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1156392 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3816. Min Act: -0.0000

Data Index: 505705 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1845626 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3984. Min Act: -0.0000

Data Index: 931455 (The Pile)

Max Activating Token Index: 417