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

Dataset: The Pile

Neuron 1360 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: 0.7029. Min Range: -0.7029

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1494585 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1653156 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1587459 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.6310. Min Act: -0.0000

Data Index: 363056 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5469. Min Act: -0.0000

Data Index: 454209 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5466. Min Act: 0.0000

Data Index: 166394 (The Pile)

Max Activating Token Index: 732

Text #6

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1323342 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1557778 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1931498 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1998305 (The Pile)

Max Activating Token Index: 187

Text #10

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5331. Min Act: -0.0000

Data Index: 987273 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5334. Min Act: -0.0000

Data Index: 927520 (The Pile)

Max Activating Token Index: 940

Text #12

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1159457 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1004323 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1735294 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1094349 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.4816. Min Act: 0.0001

Data Index: 347837 (The Pile)

Max Activating Token Index: 822

Text #17

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1489859 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5119. Min Act: -0.0000

Data Index: 962977 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.7029. Min Range: -0.7029

Max Act: 0.5093. Min Act: -0.0000

Data Index: 805760 (The Pile)

Max Activating Token Index: 234