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

Dataset: The Pile

Neuron 161 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1850. Min Range: -5.1850

Max Act: 5.1850. Min Act: -0.0000

Data Index: 1561267 (The Pile)

Max Activating Token Index: 80

Text #1

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.9446. Min Act: -0.0000

Data Index: 1612825 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.8660. Min Act: -0.0000

Data Index: 194435 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.7263. Min Act: -0.0000

Data Index: 649885 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.5874. Min Act: -0.0000

Data Index: 1293925 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.5395. Min Act: -0.0000

Data Index: 1912355 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.8304. Min Act: -0.0000

Data Index: 1244183 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.6098. Min Act: -0.0000

Data Index: 492512 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.2885. Min Act: -0.0000

Data Index: 495597 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.3856. Min Act: -0.0000

Data Index: 818273 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.3516. Min Act: -0.0000

Data Index: 219315 (The Pile)

Max Activating Token Index: 710

Text #11

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.1601. Min Act: -0.0000

Data Index: 78657 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 5.1850. Min Range: -5.1850

Max Act: 3.9839. Min Act: -0.0000

Data Index: 1324866 (The Pile)

Max Activating Token Index: 75

Text #13

Max Range: 5.1850. Min Range: -5.1850

Max Act: 3.9425. Min Act: -0.0000

Data Index: 1026745 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.0613. Min Act: -0.0000

Data Index: 621697 (The Pile)

Max Activating Token Index: 739

Text #15

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.2574. Min Act: -0.0000

Data Index: 953879 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.0764. Min Act: -0.0000

Data Index: 1115665 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.2552. Min Act: -0.0000

Data Index: 751874 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.0817. Min Act: -0.0000

Data Index: 1991861 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 5.1850. Min Range: -5.1850

Max Act: 4.0498. Min Act: -0.0000

Data Index: 97591 (The Pile)

Max Activating Token Index: 539