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

Dataset: The Pile

Neuron 4441 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: 1.1399. Min Range: -1.1399

Max Act: 1.1399. Min Act: -0.0000

Data Index: 569891 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.9419. Min Act: -0.0000

Data Index: 665426 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1085356 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1251832 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1512090 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1804627 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.6100. Min Act: -0.0000

Data Index: 849904 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1983280 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1206977 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1763217 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1038453 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5871. Min Act: -0.0000

Data Index: 376830 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1165840 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1632683 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1954299 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.6071. Min Act: -0.0000

Data Index: 667073 (The Pile)

Max Activating Token Index: 83

Text #16

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1376430 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5308. Min Act: -0.0000

Data Index: 95166 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5704. Min Act: -0.0000

Data Index: 124267 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 1.1399. Min Range: -1.1399

Max Act: 0.5353. Min Act: -0.0000

Data Index: 555124 (The Pile)

Max Activating Token Index: 38