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

Dataset: The Pile

Neuron 2290 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: 0.4669. Min Range: -0.4669

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1475788 (The Pile)

Max Activating Token Index: 969

Text #1

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.4669. Min Act: -0.0000

Data Index: 752301 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1551662 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3938. Min Act: -0.0000

Data Index: 121584 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1968135 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3847. Min Act: -0.0000

Data Index: 419998 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3639. Min Act: -0.0000

Data Index: 446539 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1279609 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1853686 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3668. Min Act: -0.0000

Data Index: 456736 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3280. Min Act: -0.0000

Data Index: 637223 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1407533 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1948911 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1830002 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3393. Min Act: -0.0000

Data Index: 747134 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1545400 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1738834 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1014901 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1873268 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1897896 (The Pile)

Max Activating Token Index: 743