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

Dataset: The Pile

Neuron 2998 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1024. Min Range: -1.1024

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1832557 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 1.1024. Min Range: -1.1024

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1946107 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.9912. Min Act: -0.0000

Data Index: 546106 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8791. Min Act: -0.0000

Data Index: 659022 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7653. Min Act: -0.0000

Data Index: 741134 (The Pile)

Max Activating Token Index: 633

Text #5

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7843. Min Act: -0.0000

Data Index: 749720 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1873920 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7485. Min Act: -0.0000

Data Index: 66330 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7436. Min Act: -0.0000

Data Index: 112585 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6559. Min Act: -0.0000

Data Index: 406482 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1079666 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1209507 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1223067 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1010929 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5729. Min Act: -0.0000

Data Index: 972540 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6333. Min Act: -0.0000

Data Index: 196437 (The Pile)

Max Activating Token Index: 505

Text #16

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1247649 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5894. Min Act: -0.0000

Data Index: 720201 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1861286 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1734397 (The Pile)

Max Activating Token Index: 921