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

Dataset: The Pile

Neuron 1062 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: 0.5139. Min Range: -0.5139

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1389562 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4662. Min Act: -0.0000

Data Index: 573829 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4710. Min Act: -0.0000

Data Index: 421385 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3985. Min Act: -0.0000

Data Index: 380462 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1666876 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1893872 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3887. Min Act: -0.0000

Data Index: 614150 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3790. Min Act: -0.0000

Data Index: 404966 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1595326 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1262815 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1697532 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3917. Min Act: -0.0000

Data Index: 244074 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1976731 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1881718 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1816954 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1664811 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1566510 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1810639 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1077591 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3528. Min Act: -0.0000

Data Index: 884746 (The Pile)

Max Activating Token Index: 320