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

Dataset: The Pile

Neuron 2297 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: 0.9201. Min Range: -0.9201

Max Act: 0.9201. Min Act: -0.0000

Data Index: 34068 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.8599. Min Act: -0.0000

Data Index: 392005 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.8795. Min Act: -0.0000

Data Index: 440055 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.8601. Min Act: -0.0000

Data Index: 283017 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.8627. Min Act: -0.0000

Data Index: 171549 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1749929 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7033. Min Act: -0.0000

Data Index: 483550 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7164. Min Act: -0.0000

Data Index: 871358 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7143. Min Act: -0.0000

Data Index: 454911 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1835915 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1471803 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1552138 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.7247. Min Act: -0.0000

Data Index: 877421 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6601. Min Act: -0.0000

Data Index: 611844 (The Pile)

Max Activating Token Index: 191

Text #14

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6214. Min Act: -0.0000

Data Index: 568302 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1618272 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1085568 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1520916 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1005118 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 0.9201. Min Range: -0.9201

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1039192 (The Pile)

Max Activating Token Index: 529