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

Dataset: The Pile

Neuron 156 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0640. Min Range: -1.0640

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1323165 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.7255. Min Act: -0.0000

Data Index: 402514 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6895. Min Act: -0.0000

Data Index: 105359 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1079626 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5393. Min Act: -0.0000

Data Index: 659922 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6349. Min Act: -0.0000

Data Index: 963477 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5580. Min Act: -0.0000

Data Index: 771334 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5851. Min Act: -0.0000

Data Index: 234751 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1782796 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1176252 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1800691 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5414. Min Act: -0.0000

Data Index: 433295 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5017. Min Act: -0.0000

Data Index: 688067 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1906833 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5365. Min Act: -0.0000

Data Index: 88692 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1816987 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.4779. Min Act: -0.0000

Data Index: 735010 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1179102 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1730516 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 1.0640. Min Range: -1.0640

Max Act: 0.4876. Min Act: -0.0000

Data Index: 84131 (The Pile)

Max Activating Token Index: 176