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

Dataset: The Pile

Neuron 3524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.3889. Min Act: -0.0000

Data Index: 1072110 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.2997. Min Act: -0.0000

Data Index: 265679 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1299774 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1676. Min Act: -0.0000

Data Index: 501946 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1635. Min Act: -0.0000

Data Index: 531096 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1079339 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1457. Min Act: -0.0000

Data Index: 317693 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1752696 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0748. Min Act: -0.0000

Data Index: 668138 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1792431 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1608078 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1847851 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1609. Min Act: -0.0000

Data Index: 679591 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0838. Min Act: -0.0000

Data Index: 290813 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1890122 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0704. Min Act: -0.0000

Data Index: 596918 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.1592. Min Act: -0.0000

Data Index: 1047253 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0745. Min Act: -0.0000

Data Index: 574752 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 1.3889. Min Range: -1.3889

Max Act: 1.0619. Min Act: -0.0000

Data Index: 72781 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 1.3889. Min Range: -1.3889

Max Act: 0.9762. Min Act: -0.0000

Data Index: 885056 (The Pile)

Max Activating Token Index: 86