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

Dataset: The Pile

Neuron 328 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: 0.7861. Min Range: -0.7861

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1266126 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1734812 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1895550 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6462. Min Act: -0.0000

Data Index: 43526 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1178852 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1052622 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5364. Min Act: -0.0000

Data Index: 30436 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5253. Min Act: -0.0000

Data Index: 230708 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5480. Min Act: -0.0000

Data Index: 170076 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5378. Min Act: -0.0000

Data Index: 272616 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5541. Min Act: -0.0000

Data Index: 48488 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1851136 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1762568 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5221. Min Act: -0.0000

Data Index: 421978 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5236. Min Act: -0.0000

Data Index: 675272 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.4996. Min Act: -0.0000

Data Index: 364166 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5067. Min Act: -0.0000

Data Index: 395482 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1372512 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5038. Min Act: -0.0000

Data Index: 991290 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5246. Min Act: -0.0000

Data Index: 219650 (The Pile)

Max Activating Token Index: 141