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

Dataset: The Pile

Neuron 2662 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: 1.5524. Min Range: -1.5524

Max Act: 1.5524. Min Act: -0.0000

Data Index: 717120 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.4739. Min Act: -0.0000

Data Index: 728279 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.2998. Min Act: -0.0000

Data Index: 668637 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.2140. Min Act: -0.0000

Data Index: 229484 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1421801 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.2764. Min Act: -0.0000

Data Index: 123985 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.2006. Min Act: -0.0000

Data Index: 1728181 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.2201. Min Act: -0.0000

Data Index: 310104 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1634311 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1406. Min Act: -0.0000

Data Index: 740783 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1185922 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1090295 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1434377 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1249. Min Act: -0.0000

Data Index: 937070 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1373916 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1944184 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1547150 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.1190. Min Act: -0.0000

Data Index: 531424 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1755387 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 1.5524. Min Range: -1.5524

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1115437 (The Pile)

Max Activating Token Index: 547