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

Dataset: The Pile

Neuron 3899 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: 0.8819. Min Range: -0.8819

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1360673 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8819. Min Act: -0.0000

Data Index: 748301 (The Pile)

Max Activating Token Index: 732

Text #2

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8642. Min Act: -0.0000

Data Index: 80243 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7829. Min Act: -0.0000

Data Index: 595697 (The Pile)

Max Activating Token Index: 414

Text #4

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1326061 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1545570 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1925646 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6947. Min Act: -0.0000

Data Index: 827681 (The Pile)

Max Activating Token Index: 917

Text #8

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7221. Min Act: -0.0000

Data Index: 857260 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1978157 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1915872 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6169. Min Act: -0.0000

Data Index: 284659 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6358. Min Act: -0.0000

Data Index: 527518 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1642355 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1238068 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.5639. Min Act: -0.0000

Data Index: 31526 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6603. Min Act: -0.0000

Data Index: 132249 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.5538. Min Act: -0.0000

Data Index: 600237 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1744942 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.5747. Min Act: -0.0000

Data Index: 849582 (The Pile)

Max Activating Token Index: 645