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

Dataset: The Pile

Neuron 3317 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0803. Min Act: 0.0000

Data Index: 1436094 (The Pile)

Max Activating Token Index: 12

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0000

Data Index: 684262 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1142453 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0804. Min Act: -0.0000

Data Index: 132315 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0795. Min Act: -0.0000

Data Index: 198963 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0775. Min Act: -0.0000

Data Index: 150716 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0753. Min Act: -0.0000

Data Index: 999936 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0742. Min Act: -0.0000

Data Index: 963916 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0742. Min Act: -0.0000

Data Index: 448172 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0742. Min Act: -0.0000

Data Index: 513475 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0740. Min Act: -0.0000

Data Index: 213293 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0765. Min Act: -0.0000

Data Index: 90376 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0730. Min Act: 0.0000

Data Index: 229228 (The Pile)

Max Activating Token Index: 881

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0718. Min Act: -0.0000

Data Index: 562357 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1148154 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0687. Min Act: -0.0000

Data Index: 752345 (The Pile)

Max Activating Token Index: 17

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0708. Min Act: 0.0001

Data Index: 1852643 (The Pile)

Max Activating Token Index: 555

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1853692 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1987094 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0689. Min Act: -0.0000

Data Index: 852281 (The Pile)

Max Activating Token Index: 12