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

Dataset: The Pile

Neuron 754 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3695. Min Act: -0.0000

Data Index: 15387 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3734. Min Act: -0.0000

Data Index: 384972 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1954358 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3361. Min Act: -0.0000

Data Index: 700108 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1676640 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1472416 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3296. Min Act: -0.0000

Data Index: 865587 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1956986 (The Pile)

Max Activating Token Index: 493

Text #8

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1001549 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1549534 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2980. Min Act: -0.0000

Data Index: 857412 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1486065 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1395452 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1186398 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3300. Min Act: -0.0000

Data Index: 516069 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1866238 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2558. Min Act: -0.0000

Data Index: 780513 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2794. Min Act: -0.0000

Data Index: 201819 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1580295 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2680. Min Act: -0.0000

Data Index: 626388 (The Pile)

Max Activating Token Index: 604