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

Dataset: The Pile

Neuron 716 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: 0.7831. Min Range: -0.7831

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1888932 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1735792 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7108. Min Act: -0.0000

Data Index: 741553 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6798. Min Act: -0.0000

Data Index: 295843 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6673. Min Act: -0.0000

Data Index: 371269 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6474. Min Act: -0.0000

Data Index: 667151 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1164237 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1284285 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1855464 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6197. Min Act: -0.0000

Data Index: 670143 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6030. Min Act: -0.0000

Data Index: 725315 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1281664 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1934599 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1791559 (The Pile)

Max Activating Token Index: 908

Text #14

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6144. Min Act: -0.0000

Data Index: 606049 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1893019 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1772368 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6465. Min Act: -0.0000

Data Index: 760729 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6262. Min Act: -0.0000

Data Index: 838018 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1198330 (The Pile)

Max Activating Token Index: 406