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

Dataset: The Pile

Neuron 1546 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7655. Min Act: -0.0000

Data Index: 445070 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1868206 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7306. Min Act: -0.0000

Data Index: 785126 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1675719 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6560. Min Act: -0.0000

Data Index: 767989 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1422882 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1438347 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1544798 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1667933 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6252. Min Act: -0.0000

Data Index: 29474 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1968316 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6466. Min Act: -0.0000

Data Index: 31060 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6491. Min Act: -0.0000

Data Index: 179128 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1268333 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6196. Min Act: -0.0000

Data Index: 542734 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1337580 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6203. Min Act: -0.0000

Data Index: 765451 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6212. Min Act: -0.0000

Data Index: 95747 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5737. Min Act: -0.0000

Data Index: 662093 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5670. Min Act: -0.0000

Data Index: 400543 (The Pile)

Max Activating Token Index: 126