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

Dataset: The Pile

Neuron 2506 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: 1.4797. Min Range: -1.4797

Max Act: 1.3929. Min Act: -0.0000

Data Index: 1132413 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.4797. Min Act: -0.0000

Data Index: 928927 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.4655. Min Act: 0.0000

Data Index: 605818 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1849782 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1540452 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2384. Min Act: -0.0000

Data Index: 900863 (The Pile)

Max Activating Token Index: 579

Text #6

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1756424 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1017570 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0965. Min Act: -0.0000

Data Index: 276713 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1458. Min Act: -0.0000

Data Index: 416225 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1777103 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0797. Min Act: -0.0000

Data Index: 631331 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1597213 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1072546 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0851. Min Act: -0.0000

Data Index: 348647 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0267. Min Act: -0.0000

Data Index: 1237126 (The Pile)

Max Activating Token Index: 375

Text #16

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9637. Min Act: -0.0000

Data Index: 150158 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0131. Min Act: -0.0000

Data Index: 606148 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9087. Min Act: -0.0000

Data Index: 518248 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1066036 (The Pile)

Max Activating Token Index: 38