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

Dataset: The Pile

Neuron 975 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1122. Min Range: -1.1122

Max Act: 1.1122. Min Act: -0.0000

Data Index: 262402 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1186331 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1763038 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1332627 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9366. Min Act: -0.0000

Data Index: 990759 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1178386 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8785. Min Act: -0.0000

Data Index: 718100 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8021. Min Act: -0.0000

Data Index: 151615 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8696. Min Act: -0.0000

Data Index: 160015 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7968. Min Act: -0.0000

Data Index: 188771 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1544009 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1941082 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8415. Min Act: -0.0000

Data Index: 838779 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1247669 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8475. Min Act: -0.0000

Data Index: 538597 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8297. Min Act: -0.0000

Data Index: 147327 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8011. Min Act: -0.0000

Data Index: 640482 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1435225 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1462313 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.7620. Min Act: -0.0000

Data Index: 877145 (The Pile)

Max Activating Token Index: 368