Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3552 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3768. Min Act: -0.0000

Data Index: 37890 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3098. Min Act: -0.0000

Data Index: 135832 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3261. Min Act: -0.0000

Data Index: 652700 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2719. Min Act: -0.0000

Data Index: 356016 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2481. Min Act: -0.0000

Data Index: 301339 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2750. Min Act: -0.0000

Data Index: 532376 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1561891 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2377. Min Act: -0.0000

Data Index: 585593 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2728. Min Act: -0.0000

Data Index: 148195 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1680031 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1221681 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1152762 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2503. Min Act: -0.0000

Data Index: 925929 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2454. Min Act: -0.0000

Data Index: 449030 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2155. Min Act: -0.0000

Data Index: 14158 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1688669 (The Pile)

Max Activating Token Index: 918

Text #16

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1750884 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1734325 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2327. Min Act: -0.0000

Data Index: 275946 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2005. Min Act: -0.0000

Data Index: 800065 (The Pile)

Max Activating Token Index: 809