Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1348390 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6800. Min Act: -0.0000

Data Index: 897020 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6067. Min Act: -0.0000

Data Index: 634427 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1007556 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1854165 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1730430 (The Pile)

Max Activating Token Index: 110

Text #6

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5480. Min Act: -0.0000

Data Index: 668287 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5892. Min Act: -0.0000

Data Index: 638243 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1704403 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5527. Min Act: -0.0000

Data Index: 526775 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6010. Min Act: -0.0000

Data Index: 594031 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1526519 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5494. Min Act: -0.0000

Data Index: 41075 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1169573 (The Pile)

Max Activating Token Index: 440

Text #14

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5845. Min Act: -0.0000

Data Index: 144480 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1759194 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1901697 (The Pile)

Max Activating Token Index: 75

Text #17

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1042562 (The Pile)

Max Activating Token Index: 141

Text #18

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1936111 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5398. Min Act: -0.0000

Data Index: 372355 (The Pile)

Max Activating Token Index: 254