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

Dataset: The Pile

Neuron 3016 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.4392. Min Act: -0.0000

Data Index: 1699428 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1567159 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1221933 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1579827 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0081. Min Act: -0.0000

Data Index: 1662886 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0909. Min Act: -0.0000

Data Index: 671814 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0793. Min Act: -0.0000

Data Index: 86107 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1202723 (The Pile)

Max Activating Token Index: 319

Text #8

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1328. Min Act: -0.0000

Data Index: 526776 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1538028 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9860. Min Act: -0.0000

Data Index: 652419 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0718. Min Act: -0.0000

Data Index: 4360 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0372. Min Act: -0.0000

Data Index: 498032 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1698178 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 1.4392. Min Range: -1.4392

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1350948 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9056. Min Act: -0.0000

Data Index: 29085 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9219. Min Act: -0.0000

Data Index: 235859 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1784988 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1509137 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 1.4392. Min Range: -1.4392

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1579806 (The Pile)

Max Activating Token Index: 235