Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 28 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3761. Min Act: -0.0000

Data Index: 127787 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3734. Min Act: 0.0000

Data Index: 1544907 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3422. Min Act: -0.0000

Data Index: 817749 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2961. Min Act: 0.0000

Data Index: 1083240 (The Pile)

Max Activating Token Index: 967

Text #4

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2958. Min Act: 0.0000

Data Index: 884006 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2503. Min Act: -0.0000

Data Index: 548134 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1187680 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2690. Min Act: -0.0000

Data Index: 304683 (The Pile)

Max Activating Token Index: 648

Text #8

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1336139 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2517. Min Act: -0.0000

Data Index: 467822 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2597. Min Act: -0.0000

Data Index: 677947 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2603. Min Act: -0.0000

Data Index: 781415 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2553. Min Act: -0.0000

Data Index: 73522 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2652. Min Act: -0.0000

Data Index: 699603 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2569. Min Act: -0.0000

Data Index: 447073 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2519. Min Act: 0.0000

Data Index: 1161945 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2486. Min Act: 0.0000

Data Index: 1822339 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1521301 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1537292 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1950869 (The Pile)

Max Activating Token Index: 691