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

Dataset: The Pile

Neuron 460 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: 1.3073. Min Range: -1.3073

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1160446 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9342. Min Act: -0.0000

Data Index: 43268 (The Pile)

Max Activating Token Index: 348

Text #2

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1105501 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1695842 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1656267 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1841638 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.9067. Min Act: -0.0000

Data Index: 390525 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8203. Min Act: -0.0000

Data Index: 581261 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.7715. Min Act: -0.0000

Data Index: 230761 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.7128. Min Act: -0.0000

Data Index: 681309 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1672448 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8032. Min Act: -0.0000

Data Index: 984833 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.7648. Min Act: -0.0000

Data Index: 853330 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.6623. Min Act: -0.0000

Data Index: 30573 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1906670 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.8067. Min Act: -0.0000

Data Index: 643581 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1099343 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.6885. Min Act: -0.0000

Data Index: 380112 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1303681 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 1.3073. Min Range: -1.3073

Max Act: 0.6907. Min Act: -0.0000

Data Index: 251104 (The Pile)

Max Activating Token Index: 3