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

Dataset: The Pile

Neuron 2236 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: 0.3127. Min Range: -0.3127

Max Act: 0.3127. Min Act: -0.0000

Data Index: 822888 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.2097. Min Act: -0.0000

Data Index: 657026 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1985. Min Act: -0.0000

Data Index: 398623 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1850. Min Act: -0.0000

Data Index: 222803 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1570160 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1762. Min Act: -0.0000

Data Index: 959147 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1936. Min Act: -0.0000

Data Index: 993228 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1678. Min Act: -0.0000

Data Index: 205329 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1064852 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1668. Min Act: -0.0000

Data Index: 8148 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1718. Min Act: -0.0000

Data Index: 977617 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1712. Min Act: -0.0000

Data Index: 583000 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1493867 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1619. Min Act: -0.0000

Data Index: 874864 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1809649 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1529. Min Act: -0.0000

Data Index: 714948 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1835419 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1154708 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1501458 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 0.3127. Min Range: -0.3127

Max Act: 0.1530. Min Act: -0.0000

Data Index: 413279 (The Pile)

Max Activating Token Index: 278