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

Dataset: The Pile

Neuron 3818 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1930713 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1487900 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4519. Min Act: 0.0000

Data Index: 118816 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1374944 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1745488 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3910. Min Act: -0.0000

Data Index: 87402 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1884441 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3801. Min Act: -0.0000

Data Index: 200562 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3715. Min Act: -0.0000

Data Index: 995812 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1214005 (The Pile)

Max Activating Token Index: 467

Text #10

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1421898 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3802. Min Act: -0.0000

Data Index: 586642 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3906. Min Act: -0.0000

Data Index: 911565 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3616. Min Act: 0.0000

Data Index: 1577882 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3779. Min Act: -0.0000

Data Index: 832314 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1068652 (The Pile)

Max Activating Token Index: 302

Text #16

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1595148 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3658. Min Act: -0.0000

Data Index: 598151 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3545. Min Act: -0.0000

Data Index: 433477 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3734. Min Act: -0.0000

Data Index: 566589 (The Pile)

Max Activating Token Index: 774