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

Dataset: The Pile

Neuron 2524 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: 1.9698. Min Range: -1.9698

Max Act: 1.9487. Min Act: -0.0000

Data Index: 775864 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.9698. Min Act: -0.0000

Data Index: 1279577 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.7372. Min Act: -0.0000

Data Index: 29035 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.5730. Min Act: -0.0000

Data Index: 1272046 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.6480. Min Act: -0.0000

Data Index: 1760133 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.5440. Min Act: -0.0000

Data Index: 680350 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.4529. Min Act: -0.0000

Data Index: 673894 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.5495. Min Act: -0.0000

Data Index: 1015692 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.4668. Min Act: -0.0000

Data Index: 874329 (The Pile)

Max Activating Token Index: 244

Text #9

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1257790 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1814672 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.3547. Min Act: -0.0000

Data Index: 980372 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1586676 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1873592 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.3711. Min Act: -0.0000

Data Index: 204967 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1861747 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.3562. Min Act: -0.0000

Data Index: 250 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.4074. Min Act: -0.0000

Data Index: 447238 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.6003. Min Act: -0.0000

Data Index: 294804 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 1.9698. Min Range: -1.9698

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1112109 (The Pile)

Max Activating Token Index: 150