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

Dataset: The Pile

Neuron 2305 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: 0.5364. Min Range: -0.5364

Max Act: 0.5364. Min Act: -0.0000

Data Index: 688737 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.5224. Min Act: 0.0000

Data Index: 819775 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.5101. Min Act: 0.0004

Data Index: 1817771 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1617541 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.5081. Min Act: -0.0000

Data Index: 462927 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1856729 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4287. Min Act: -0.0000

Data Index: 564149 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4579. Min Act: -0.0000

Data Index: 122425 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4794. Min Act: -0.0000

Data Index: 743634 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4504. Min Act: -0.0000

Data Index: 726310 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1278853 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1853761 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4839. Min Act: -0.0000

Data Index: 663405 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1718477 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4679. Min Act: 0.0000

Data Index: 662774 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4819. Min Act: 0.0003

Data Index: 974750 (The Pile)

Max Activating Token Index: 446

Text #16

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4702. Min Act: -0.0000

Data Index: 20198 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4719. Min Act: -0.0000

Data Index: 906354 (The Pile)

Max Activating Token Index: 850

Text #18

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4497. Min Act: -0.0000

Data Index: 974937 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 0.5364. Min Range: -0.5364

Max Act: 0.4302. Min Act: -0.0000

Data Index: 713532 (The Pile)

Max Activating Token Index: 499