Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2307 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1196394 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1980978 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1506102 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1852834 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5504. Min Act: -0.0000

Data Index: 544604 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5300. Min Act: -0.0000

Data Index: 930304 (The Pile)

Max Activating Token Index: 1008

Text #6

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1704131 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4867. Min Act: -0.0000

Data Index: 270393 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1425179 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4595. Min Act: -0.0000

Data Index: 858284 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4727. Min Act: -0.0000

Data Index: 522758 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1364670 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1464943 (The Pile)

Max Activating Token Index: 186

Text #13

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4647. Min Act: -0.0001

Data Index: 1509202 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1531175 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4786. Min Act: -0.0000

Data Index: 364790 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1371523 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4474. Min Act: -0.0000

Data Index: 792136 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1897477 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4672. Min Act: -0.0000

Data Index: 590098 (The Pile)

Max Activating Token Index: 563