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

Dataset: The Pile

Neuron 2388 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: 0.9243. Min Range: -0.9243

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1812176 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1821762 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1288762 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1059524 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1429327 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7067. Min Act: -0.0000

Data Index: 240204 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7186. Min Act: -0.0000

Data Index: 663992 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1085991 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6707. Min Act: -0.0000

Data Index: 735938 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6660. Min Act: -0.0000

Data Index: 560248 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6341. Min Act: -0.0000

Data Index: 788210 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1228778 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1434087 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1148846 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1760323 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6039. Min Act: -0.0000

Data Index: 463041 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6150. Min Act: -0.0000

Data Index: 16190 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6015. Min Act: -0.0000

Data Index: 874000 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.5251. Min Act: -0.0000

Data Index: 341687 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.5814. Min Act: -0.0000

Data Index: 73362 (The Pile)

Max Activating Token Index: 185