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

Dataset: The Pile

Neuron 1144 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: 1.0875. Min Range: -1.0875

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1321737 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 1.0875. Min Range: -1.0875

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1549213 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9940. Min Act: -0.0000

Data Index: 179830 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 1.0875. Min Range: -1.0875

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1043953 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 1.0875. Min Range: -1.0875

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1735566 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9580. Min Act: -0.0000

Data Index: 82320 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1677168 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9098. Min Act: -0.0000

Data Index: 291539 (The Pile)

Max Activating Token Index: 907

Text #8

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9253. Min Act: -0.0000

Data Index: 524254 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1704749 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9333. Min Act: -0.0000

Data Index: 388324 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8428. Min Act: -0.0000

Data Index: 280889 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1309225 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8552. Min Act: -0.0000

Data Index: 147231 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1160840 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1515034 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8798. Min Act: -0.0000

Data Index: 734903 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1880479 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1615742 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.7743. Min Act: -0.0000

Data Index: 229784 (The Pile)

Max Activating Token Index: 57