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

Dataset: The Pile

Neuron 75 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: 0.7308. Min Range: -0.7308

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1572247 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1750917 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1248290 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6795. Min Act: -0.0000

Data Index: 186079 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1418640 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6445. Min Act: -0.0000

Data Index: 238174 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1683531 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6448. Min Act: -0.0000

Data Index: 483771 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1167614 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6080. Min Act: -0.0000

Data Index: 498401 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5853. Min Act: -0.0000

Data Index: 921007 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5578. Min Act: -0.0000

Data Index: 479430 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1137636 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5417. Min Act: -0.0000

Data Index: 407424 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1489240 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5206. Min Act: -0.0000

Data Index: 76930 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5174. Min Act: -0.0000

Data Index: 786536 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1302394 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.4825. Min Act: -0.0000

Data Index: 772077 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5112. Min Act: -0.0000

Data Index: 529596 (The Pile)

Max Activating Token Index: 280