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

Dataset: The Pile

Neuron 2706 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: 1.5789. Min Range: -1.5789

Max Act: 1.4464. Min Act: -0.0000

Data Index: 881171 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.4488. Min Act: -0.0000

Data Index: 10233 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.5088. Min Act: -0.0000

Data Index: 1369126 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.5789. Min Act: -0.0000

Data Index: 1674823 (The Pile)

Max Activating Token Index: 584

Text #4

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.3655. Min Act: -0.0000

Data Index: 99282 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1745324 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1693210 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1720. Min Act: -0.0000

Data Index: 1241653 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.3180. Min Act: -0.0000

Data Index: 423046 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1813812 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1987126 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1450. Min Act: -0.0000

Data Index: 512229 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2826. Min Act: -0.0000

Data Index: 83602 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1077790 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1425. Min Act: 0.0000

Data Index: 1934068 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1433126 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1190. Min Act: -0.0000

Data Index: 921223 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1067. Min Act: -0.0000

Data Index: 285641 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1417525 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1530002 (The Pile)

Max Activating Token Index: 545