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

Dataset: The Pile

Neuron 2990 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: 0.9299. Min Range: -0.9299

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1168812 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.9192. Min Act: -0.0000

Data Index: 560253 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.9123. Min Act: -0.0000

Data Index: 71882 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8864. Min Act: -0.0000

Data Index: 172264 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8380. Min Act: -0.0000

Data Index: 583277 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7193. Min Act: -0.0000

Data Index: 734318 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1009665 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7736. Min Act: -0.0000

Data Index: 652853 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1715441 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7266. Min Act: -0.0000

Data Index: 866954 (The Pile)

Max Activating Token Index: 572

Text #10

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1579313 (The Pile)

Max Activating Token Index: 915

Text #11

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7222. Min Act: -0.0000

Data Index: 565608 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6870. Min Act: -0.0000

Data Index: 577421 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6450. Min Act: -0.0000

Data Index: 324762 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6802. Min Act: -0.0000

Data Index: 280109 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6182. Min Act: -0.0000

Data Index: 896126 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1774502 (The Pile)

Max Activating Token Index: 822

Text #17

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1697168 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1228482 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6500. Min Act: -0.0000

Data Index: 149349 (The Pile)

Max Activating Token Index: 390