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

Dataset: The Pile

Neuron 795 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: 0.7054. Min Range: -0.7054

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1922084 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1391233 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1071656 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1061467 (The Pile)

Max Activating Token Index: 721

Text #4

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1142025 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1290881 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6305. Min Act: -0.0000

Data Index: 390325 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1081110 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1398883 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6173. Min Act: -0.0000

Data Index: 113883 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1803299 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1554749 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5841. Min Act: -0.0000

Data Index: 581292 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5905. Min Act: -0.0000

Data Index: 812717 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1083245 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5813. Min Act: -0.0000

Data Index: 482740 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1814479 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1327936 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5695. Min Act: -0.0000

Data Index: 312814 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 0.7054. Min Range: -0.7054

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1999184 (The Pile)

Max Activating Token Index: 296