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

Dataset: The Pile

Neuron 2838 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1088425 (The Pile)

Max Activating Token Index: 594

Text #1

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.1632. Min Act: -0.0000

Data Index: 102139 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.1831. Min Act: -0.0000

Data Index: 729086 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1901570 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.1261. Min Act: -0.0000

Data Index: 650981 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9920. Min Act: -0.0000

Data Index: 184863 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0546. Min Act: -0.0000

Data Index: 549845 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0619. Min Act: -0.0000

Data Index: 706001 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0003. Min Act: -0.0000

Data Index: 352734 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0275. Min Act: -0.0000

Data Index: 184022 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9736. Min Act: -0.0000

Data Index: 393184 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 1.2752. Min Range: -1.2752

Max Act: 1.0163. Min Act: -0.0000

Data Index: 121233 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9824. Min Act: -0.0000

Data Index: 447798 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1717764 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9931. Min Act: -0.0000

Data Index: 666226 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1730680 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1131802 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1007884 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.9122. Min Act: -0.0000

Data Index: 228822 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 1.2752. Min Range: -1.2752

Max Act: 0.8942. Min Act: -0.0000

Data Index: 329255 (The Pile)

Max Activating Token Index: 948