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

Dataset: The Pile

Neuron 27 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: 1.0448. Min Range: -1.0448

Max Act: 1.0448. Min Act: -0.0000

Data Index: 703884 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1670794 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1333241 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6934. Min Act: 0.0000

Data Index: 326032 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1227030 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.7182. Min Act: -0.0000

Data Index: 268019 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.7089. Min Act: -0.0000

Data Index: 131660 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1824827 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1722048 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6859. Min Act: -0.0000

Data Index: 781488 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1496537 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6349. Min Act: -0.0000

Data Index: 970192 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6391. Min Act: -0.0000

Data Index: 139719 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1513026 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6386. Min Act: -0.0000

Data Index: 595788 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1934569 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6508. Min Act: -0.0000

Data Index: 985631 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6535. Min Act: -0.0000

Data Index: 143740 (The Pile)

Max Activating Token Index: 521

Text #18

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1328369 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.5638. Min Act: -0.0000

Data Index: 303316 (The Pile)

Max Activating Token Index: 380