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

Dataset: The Pile

Neuron 3465 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1283627 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1057120 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1385423 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1002968 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8930. Min Act: -0.0000

Data Index: 676187 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9189. Min Act: -0.0000

Data Index: 600206 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9248. Min Act: -0.0000

Data Index: 304738 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1866962 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8448. Min Act: -0.0000

Data Index: 142252 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9385. Min Act: -0.0000

Data Index: 264465 (The Pile)

Max Activating Token Index: 781

Text #10

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8424. Min Act: -0.0000

Data Index: 11454 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8104. Min Act: -0.0000

Data Index: 48508 (The Pile)

Max Activating Token Index: 831

Text #12

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8336. Min Act: -0.0000

Data Index: 823968 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.7875. Min Act: -0.0000

Data Index: 318918 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8145. Min Act: -0.0000

Data Index: 583456 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1772613 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1530561 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1080961 (The Pile)

Max Activating Token Index: 934

Text #18

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8240. Min Act: -0.0000

Data Index: 514268 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1976274 (The Pile)

Max Activating Token Index: 876