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

Dataset: The Pile

Neuron 1284 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3248. Min Range: -1.3248

Max Act: 1.3248. Min Act: -0.0000

Data Index: 527 (The Pile)

Max Activating Token Index: 217

Text #1

Max Range: 1.3248. Min Range: -1.3248

Max Act: 1.0812. Min Act: -0.0000

Data Index: 249077 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 1.3248. Min Range: -1.3248

Max Act: 1.1330. Min Act: -0.0000

Data Index: 415062 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 1.3248. Min Range: -1.3248

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1212976 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1631226 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.9190. Min Act: -0.0000

Data Index: 248267 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1825139 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1257983 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.8725. Min Act: -0.0000

Data Index: 568264 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1101479 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7998. Min Act: -0.0000

Data Index: 629951 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1282341 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.9238. Min Act: -0.0000

Data Index: 639933 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1368962 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7624. Min Act: -0.0000

Data Index: 865230 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1589577 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7736. Min Act: -0.0000

Data Index: 265686 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1316647 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1788713 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 1.3248. Min Range: -1.3248

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1447400 (The Pile)

Max Activating Token Index: 530