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

Dataset: The Pile

Neuron 5071 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5181. Min Range: -5.5181

Max Act: 5.5181. Min Act: -0.0000

Data Index: 939856 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 5.5181. Min Range: -5.5181

Max Act: 4.2871. Min Act: -0.0000

Data Index: 1768662 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 5.5181. Min Range: -5.5181

Max Act: 4.2468. Min Act: -0.0000

Data Index: 995402 (The Pile)

Max Activating Token Index: 560

Text #3

Max Range: 5.5181. Min Range: -5.5181

Max Act: 4.0417. Min Act: -0.0000

Data Index: 578682 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.9186. Min Act: 0.0000

Data Index: 507951 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.7441. Min Act: -0.0000

Data Index: 1038729 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 5.5181. Min Range: -5.5181

Max Act: 4.0563. Min Act: -0.0000

Data Index: 310619 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 5.5181. Min Range: -5.5181

Max Act: 4.0221. Min Act: -0.0000

Data Index: 1844422 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.7704. Min Act: -0.0000

Data Index: 152093 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.9022. Min Act: -0.0000

Data Index: 1277045 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.6935. Min Act: -0.0000

Data Index: 1263582 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.5603. Min Act: -0.0000

Data Index: 1416157 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.6562. Min Act: -0.0000

Data Index: 1027579 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.3173. Min Act: -0.0000

Data Index: 1675093 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.3889. Min Act: -0.0000

Data Index: 785757 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.3741. Min Act: -0.0000

Data Index: 542906 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.3826. Min Act: -0.0000

Data Index: 1519714 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.4077. Min Act: -0.0000

Data Index: 1758576 (The Pile)

Max Activating Token Index: 620

Text #18

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.2447. Min Act: -0.0000

Data Index: 470724 (The Pile)

Max Activating Token Index: 252

Text #19

Max Range: 5.5181. Min Range: -5.5181

Max Act: 3.3564. Min Act: -0.0000

Data Index: 1723372 (The Pile)

Max Activating Token Index: 773