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

Dataset: The Pile

Neuron 399 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: 0.7874. Min Range: -0.7874

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1539579 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1297611 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1956325 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1660796 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1212388 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1183396 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1044329 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6120. Min Act: -0.0000

Data Index: 639404 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5618. Min Act: -0.0000

Data Index: 522209 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1104968 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5823. Min Act: -0.0000

Data Index: 203099 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5865. Min Act: -0.0000

Data Index: 169890 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6036. Min Act: -0.0000

Data Index: 580153 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1411980 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1276198 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1552777 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5771. Min Act: -0.0000

Data Index: 492044 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5832. Min Act: 0.0000

Data Index: 116183 (The Pile)

Max Activating Token Index: 27

Text #18

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5576. Min Act: -0.0000

Data Index: 811131 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1085598 (The Pile)

Max Activating Token Index: 547