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

Dataset: The Pile

Neuron 3610 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.8296. Min Act: -0.0000

Data Index: 1910824 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.5895. Min Act: -0.0000

Data Index: 394955 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.6728. Min Act: -0.0000

Data Index: 773657 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.7183. Min Act: -0.0000

Data Index: 492800 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1861305 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.6812. Min Act: -0.0000

Data Index: 374517 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.7238. Min Act: -0.0000

Data Index: 1083105 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.7187. Min Act: -0.0000

Data Index: 19998 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1913187 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.6114. Min Act: -0.0000

Data Index: 176401 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.6502. Min Act: -0.0000

Data Index: 1391622 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.5882. Min Act: -0.0000

Data Index: 165194 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1181187 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.5042. Min Act: -0.0000

Data Index: 44518 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1329132 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.5320. Min Act: -0.0000

Data Index: 354237 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.7982. Min Act: -0.0000

Data Index: 311040 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.4344. Min Act: -0.0000

Data Index: 133542 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.4733. Min Act: -0.0000

Data Index: 934443 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 1.8296. Min Range: -1.8296

Max Act: 1.4691. Min Act: -0.0000

Data Index: 175177 (The Pile)

Max Activating Token Index: 738