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

Dataset: The Pile

Neuron 2586 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6231. Min Act: -0.0000

Data Index: 824045 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1415397 (The Pile)

Max Activating Token Index: 825

Text #2

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1140402 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1684659 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1703734 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1524487 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1793141 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5588. Min Act: -0.0000

Data Index: 885026 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6014. Min Act: -0.0000

Data Index: 824816 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5843. Min Act: -0.0000

Data Index: 943218 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1796902 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1860014 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1515469 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1912186 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1724680 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5455. Min Act: -0.0000

Data Index: 923020 (The Pile)

Max Activating Token Index: 366

Text #16

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1323667 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6213. Min Act: -0.0000

Data Index: 221262 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5077. Min Act: -0.0000

Data Index: 645916 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1027632 (The Pile)

Max Activating Token Index: 787