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

Dataset: The Pile

Neuron 3266 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: 0.7420. Min Range: -0.7420

Max Act: 0.7420. Min Act: -0.0000

Data Index: 864718 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1973302 (The Pile)

Max Activating Token Index: 408

Text #2

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5853. Min Act: -0.0000

Data Index: 318530 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1996180 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5473. Min Act: -0.0000

Data Index: 655046 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5627. Min Act: -0.0000

Data Index: 444965 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5505. Min Act: -0.0000

Data Index: 341854 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1179373 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1480615 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1327513 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5509. Min Act: -0.0000

Data Index: 567577 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1816005 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1323383 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5498. Min Act: -0.0000

Data Index: 339855 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1575726 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1620906 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5081. Min Act: -0.0000

Data Index: 162463 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1112411 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5058. Min Act: -0.0000

Data Index: 200902 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.7420. Min Range: -0.7420

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1719522 (The Pile)

Max Activating Token Index: 457