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

Dataset: The Pile

Neuron 3611 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: 1.5473. Min Range: -1.5473

Max Act: 1.5473. Min Act: -0.0000

Data Index: 391024 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2168. Min Act: -0.0000

Data Index: 163382 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.4983. Min Act: -0.0000

Data Index: 1057340 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.4807. Min Act: -0.0000

Data Index: 1958322 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1434679 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.3582. Min Act: -0.0000

Data Index: 236720 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1683254 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1928. Min Act: -0.0000

Data Index: 422491 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1107793 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1749. Min Act: -0.0000

Data Index: 810366 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2933. Min Act: -0.0000

Data Index: 552812 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2196. Min Act: -0.0000

Data Index: 517793 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1398. Min Act: -0.0000

Data Index: 512747 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2074. Min Act: -0.0000

Data Index: 326206 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1995. Min Act: -0.0000

Data Index: 644571 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1599251 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2640. Min Act: -0.0000

Data Index: 1659086 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 1.5473. Min Range: -1.5473

Max Act: 0.9400. Min Act: -0.0000

Data Index: 115919 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1303809 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 1.5473. Min Range: -1.5473

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1263755 (The Pile)

Max Activating Token Index: 309