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

Dataset: The Pile

Neuron 1296 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: 0.7214. Min Range: -0.7214

Max Act: 0.7214. Min Act: -0.0000

Data Index: 401160 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1239059 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1734366 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5182. Min Act: -0.0000

Data Index: 783528 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4891. Min Act: -0.0000

Data Index: 845831 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1757918 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1916824 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4945. Min Act: -0.0000

Data Index: 782648 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.5224. Min Act: -0.0000

Data Index: 614574 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4895. Min Act: -0.0000

Data Index: 148506 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1242193 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1796920 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4754. Min Act: -0.0000

Data Index: 752138 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1653577 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4646. Min Act: -0.0000

Data Index: 218319 (The Pile)

Max Activating Token Index: 457

Text #15

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4668. Min Act: -0.0000

Data Index: 684760 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4594. Min Act: -0.0000

Data Index: 34688 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1559081 (The Pile)

Max Activating Token Index: 925

Text #18

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4793. Min Act: -0.0000

Data Index: 616717 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.7214. Min Range: -0.7214

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1426996 (The Pile)

Max Activating Token Index: 586