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

Dataset: The Pile

Neuron 3675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1727261 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.6242. Min Act: -0.0000

Data Index: 333173 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.6251. Min Act: -0.0000

Data Index: 495543 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1733082 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.6081. Min Act: -0.0000

Data Index: 157074 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5740. Min Act: -0.0000

Data Index: 780383 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1786311 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5689. Min Act: -0.0000

Data Index: 950138 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1783253 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5722. Min Act: -0.0000

Data Index: 552886 (The Pile)

Max Activating Token Index: 200

Text #10

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.6137. Min Act: -0.0000

Data Index: 674101 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5863. Min Act: -0.0000

Data Index: 35528 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1080273 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1052654 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1913547 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1142480 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.4990. Min Act: -0.0000

Data Index: 314456 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1225982 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1330777 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5022. Min Act: -0.0000

Data Index: 366235 (The Pile)

Max Activating Token Index: 184