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

Dataset: The Pile

Neuron 190 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: 1.1013. Min Range: -1.1013

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1427928 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1343435 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1596154 (The Pile)

Max Activating Token Index: 740

Text #3

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8959. Min Act: -0.0000

Data Index: 91605 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1601429 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8139. Min Act: -0.0000

Data Index: 977162 (The Pile)

Max Activating Token Index: 329

Text #6

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.9753. Min Act: -0.0000

Data Index: 883449 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1022285 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1854877 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1832142 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1546887 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1177110 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1290814 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7627. Min Act: -0.0000

Data Index: 645987 (The Pile)

Max Activating Token Index: 303

Text #14

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7137. Min Act: -0.0000

Data Index: 391155 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7875. Min Act: -0.0000

Data Index: 908019 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7893. Min Act: -0.0000

Data Index: 49977 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1276789 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1360010 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.1013. Min Range: -1.1013

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1230706 (The Pile)

Max Activating Token Index: 232