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

Dataset: The Pile

Neuron 1591 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1728246 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1472792 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5139. Min Act: -0.0000

Data Index: 549548 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5880. Min Act: -0.0000

Data Index: 246626 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1167706 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5486. Min Act: -0.0000

Data Index: 937521 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5674. Min Act: -0.0000

Data Index: 16889 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1843382 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1913562 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5214. Min Act: -0.0000

Data Index: 212914 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5190. Min Act: -0.0000

Data Index: 707052 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4809. Min Act: -0.0000

Data Index: 69952 (The Pile)

Max Activating Token Index: 741

Text #12

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1363809 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1195454 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1080569 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5054. Min Act: -0.0000

Data Index: 424330 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4723. Min Act: -0.0000

Data Index: 136949 (The Pile)

Max Activating Token Index: 918

Text #17

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1247984 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1900148 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4542. Min Act: -0.0000

Data Index: 180391 (The Pile)

Max Activating Token Index: 459