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

Dataset: The Pile

Neuron 1192 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1342580 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.7055. Min Act: -0.0000

Data Index: 327922 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1531923 (The Pile)

Max Activating Token Index: 79

Text #3

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1364113 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1393508 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6992. Min Act: -0.0000

Data Index: 878625 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1066912 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1462955 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1974193 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1374432 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1884904 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6140. Min Act: -0.0000

Data Index: 691935 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1187713 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6005. Min Act: -0.0000

Data Index: 435375 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1572286 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1886006 (The Pile)

Max Activating Token Index: 669

Text #16

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5561. Min Act: -0.0000

Data Index: 971588 (The Pile)

Max Activating Token Index: 156

Text #17

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1190753 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1338822 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1057909 (The Pile)

Max Activating Token Index: 994