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

Dataset: The Pile

Neuron 3735 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: 0.9195. Min Range: -0.9195

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1371281 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.7616. Min Act: -0.0000

Data Index: 675385 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6849. Min Act: -0.0000

Data Index: 213990 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1289968 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.7977. Min Act: -0.0000

Data Index: 934929 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1456003 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1178803 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6019. Min Act: -0.0000

Data Index: 193396 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6922. Min Act: -0.0000

Data Index: 737181 (The Pile)

Max Activating Token Index: 772

Text #9

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.7741. Min Act: -0.0000

Data Index: 672784 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.7534. Min Act: -0.0000

Data Index: 374809 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1273775 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1037170 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1908363 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.8153. Min Act: -0.0000

Data Index: 234492 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1094788 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1805682 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6515. Min Act: -0.0000

Data Index: 708108 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6481. Min Act: -0.0000

Data Index: 922137 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.6779. Min Act: -0.0000

Data Index: 783477 (The Pile)

Max Activating Token Index: 523