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

Dataset: The Pile

Neuron 686 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6329. Min Range: -4.6329

Max Act: 4.6329. Min Act: -0.0000

Data Index: 475923 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 4.6329. Min Range: -4.6329

Max Act: 4.1279. Min Act: -0.0000

Data Index: 1188042 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 4.6329. Min Range: -4.6329

Max Act: 4.1489. Min Act: -0.0000

Data Index: 1634816 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 4.6329. Min Range: -4.6329

Max Act: 4.3205. Min Act: -0.0000

Data Index: 1163559 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 4.6329. Min Range: -4.6329

Max Act: 4.1679. Min Act: -0.0000

Data Index: 407314 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 4.6329. Min Range: -4.6329

Max Act: 4.0212. Min Act: -0.0000

Data Index: 564782 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.8809. Min Act: -0.0000

Data Index: 11838 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.6831. Min Act: -0.0000

Data Index: 109915 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.6258. Min Act: -0.0000

Data Index: 1605144 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.7757. Min Act: -0.0000

Data Index: 1184094 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.5258. Min Act: -0.0000

Data Index: 1372004 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.6285. Min Act: -0.0000

Data Index: 1865765 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.7179. Min Act: -0.0000

Data Index: 1036256 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.4994. Min Act: -0.0000

Data Index: 1820267 (The Pile)

Max Activating Token Index: 557

Text #14

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.5663. Min Act: -0.0000

Data Index: 1411959 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.3807. Min Act: -0.0000

Data Index: 1383440 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.5386. Min Act: -0.0000

Data Index: 319269 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.6581. Min Act: -0.0000

Data Index: 1103795 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.5062. Min Act: -0.0000

Data Index: 1625492 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 4.6329. Min Range: -4.6329

Max Act: 3.3198. Min Act: -0.0000

Data Index: 1693013 (The Pile)

Max Activating Token Index: 172