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

Dataset: The Pile

Neuron 1589 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1583. Min Range: -5.1583

Max Act: 5.1583. Min Act: -0.0000

Data Index: 787396 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 5.1583. Min Range: -5.1583

Max Act: 5.0033. Min Act: -0.0000

Data Index: 1170034 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.8263. Min Act: -0.0000

Data Index: 1198397 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.3693. Min Act: -0.0000

Data Index: 1683333 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.3883. Min Act: -0.0000

Data Index: 486515 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.1811. Min Act: -0.0000

Data Index: 1395494 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.1457. Min Act: -0.0000

Data Index: 1373396 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.3454. Min Act: -0.0000

Data Index: 1180434 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.0609. Min Act: -0.0000

Data Index: 1082219 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.0060. Min Act: -0.0000

Data Index: 1006712 (The Pile)

Max Activating Token Index: 867

Text #10

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.1234. Min Act: -0.0000

Data Index: 379087 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 5.1583. Min Range: -5.1583

Max Act: 3.9362. Min Act: -0.0000

Data Index: 313907 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.1322. Min Act: -0.0000

Data Index: 307142 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 5.1583. Min Range: -5.1583

Max Act: 3.8913. Min Act: -0.0000

Data Index: 1556425 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 5.1583. Min Range: -5.1583

Max Act: 3.5485. Min Act: -0.0000

Data Index: 1166756 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 5.1583. Min Range: -5.1583

Max Act: 4.0038. Min Act: -0.0000

Data Index: 796105 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 5.1583. Min Range: -5.1583

Max Act: 3.8250. Min Act: -0.0000

Data Index: 1116859 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 5.1583. Min Range: -5.1583

Max Act: 3.9592. Min Act: 0.0000

Data Index: 1441869 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 5.1583. Min Range: -5.1583

Max Act: 3.7487. Min Act: -0.0000

Data Index: 1093745 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 5.1583. Min Range: -5.1583

Max Act: 3.7242. Min Act: -0.0000

Data Index: 1557307 (The Pile)

Max Activating Token Index: 509