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

Dataset: The Pile

Neuron 4868 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: 9.2668. Min Range: -9.2668

Max Act: 9.2668. Min Act: -0.0000

Data Index: 993252 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 9.2668. Min Range: -9.2668

Max Act: 8.1288. Min Act: -0.0000

Data Index: 1289672 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 9.2668. Min Range: -9.2668

Max Act: 7.5738. Min Act: -0.0000

Data Index: 298612 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 9.2668. Min Range: -9.2668

Max Act: 6.4616. Min Act: -0.0000

Data Index: 200260 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 9.2668. Min Range: -9.2668

Max Act: 5.9074. Min Act: -0.0000

Data Index: 912485 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 9.2668. Min Range: -9.2668

Max Act: 6.0081. Min Act: -0.0000

Data Index: 1745069 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 9.2668. Min Range: -9.2668

Max Act: 4.6500. Min Act: -0.0000

Data Index: 1828660 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 9.2668. Min Range: -9.2668

Max Act: 5.7689. Min Act: -0.0000

Data Index: 1219325 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 9.2668. Min Range: -9.2668

Max Act: 5.5275. Min Act: -0.0000

Data Index: 352838 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 9.2668. Min Range: -9.2668

Max Act: 4.8725. Min Act: -0.0000

Data Index: 1263236 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 9.2668. Min Range: -9.2668

Max Act: 4.9684. Min Act: -0.0000

Data Index: 1689495 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 9.2668. Min Range: -9.2668

Max Act: 4.2225. Min Act: -0.0000

Data Index: 367819 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 9.2668. Min Range: -9.2668

Max Act: 4.4710. Min Act: -0.0000

Data Index: 631934 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 9.2668. Min Range: -9.2668

Max Act: 4.8278. Min Act: -0.0000

Data Index: 443825 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 9.2668. Min Range: -9.2668

Max Act: 3.7231. Min Act: -0.0000

Data Index: 1156964 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 9.2668. Min Range: -9.2668

Max Act: 3.3940. Min Act: -0.0000

Data Index: 258907 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 9.2668. Min Range: -9.2668

Max Act: 3.7947. Min Act: -0.0000

Data Index: 205967 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 9.2668. Min Range: -9.2668

Max Act: 4.2464. Min Act: -0.0000

Data Index: 1437698 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 9.2668. Min Range: -9.2668

Max Act: 3.4925. Min Act: -0.0000

Data Index: 1383552 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 9.2668. Min Range: -9.2668

Max Act: 3.7570. Min Act: -0.0000

Data Index: 152749 (The Pile)

Max Activating Token Index: 754