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

Dataset: The Pile

Neuron 718 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1232281 (The Pile)

Max Activating Token Index: 474

Text #1

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1589984 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1079181 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1782362 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.8511. Min Act: -0.0000

Data Index: 486760 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.7389. Min Act: 0.0000

Data Index: 1889141 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1105795 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.6258. Min Act: -0.0000

Data Index: 908927 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1027046 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1847845 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1625386 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1073908 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.5285. Min Act: 0.0000

Data Index: 952664 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.5432. Min Act: -0.0000

Data Index: 169691 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1087208 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.5002. Min Act: -0.0000

Data Index: 614260 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1820289 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1877691 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.4778. Min Act: -0.0000

Data Index: 467399 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1347866 (The Pile)

Max Activating Token Index: 216