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

Dataset: The Pile

Neuron 2833 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: 0.9099. Min Range: -0.9099

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1936303 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1889353 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7185. Min Act: -0.0000

Data Index: 781056 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7082. Min Act: -0.0000

Data Index: 852450 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1891687 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1851045 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7120. Min Act: -0.0000

Data Index: 878913 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7128. Min Act: -0.0000

Data Index: 142860 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1933204 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1561056 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1663604 (The Pile)

Max Activating Token Index: 957

Text #11

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.5986. Min Act: -0.0000

Data Index: 662847 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1440139 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.6078. Min Act: -0.0000

Data Index: 149500 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1814436 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.6411. Min Act: -0.0000

Data Index: 82070 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.5814. Min Act: -0.0000

Data Index: 187822 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1603629 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.5623. Min Act: -0.0000

Data Index: 443407 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.9099. Min Range: -0.9099

Max Act: 0.5364. Min Act: -0.0000

Data Index: 816711 (The Pile)

Max Activating Token Index: 662