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

Dataset: The Pile

Neuron 3395 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: 0.9430. Min Range: -0.9430

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1013235 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1890600 (The Pile)

Max Activating Token Index: 299

Text #2

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7713. Min Act: -0.0000

Data Index: 35428 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7821. Min Act: 0.0000

Data Index: 1736032 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.7004. Min Act: -0.0000

Data Index: 291882 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6789. Min Act: -0.0000

Data Index: 816652 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6907. Min Act: -0.0000

Data Index: 309400 (The Pile)

Max Activating Token Index: 685

Text #7

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6915. Min Act: -0.0000

Data Index: 795904 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6402. Min Act: 0.0000

Data Index: 817082 (The Pile)

Max Activating Token Index: 177

Text #9

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6978. Min Act: -0.0000

Data Index: 448983 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1283374 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6590. Min Act: -0.0000

Data Index: 333298 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6542. Min Act: -0.0000

Data Index: 318632 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1676874 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1885924 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6283. Min Act: -0.0000

Data Index: 976773 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1833317 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.5453. Min Act: -0.0000

Data Index: 31170 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.5609. Min Act: 0.0000

Data Index: 1523440 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.9430. Min Range: -0.9430

Max Act: 0.5813. Min Act: -0.0000

Data Index: 450048 (The Pile)

Max Activating Token Index: 714