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

Dataset: The Pile

Neuron 1847 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2188. Min Range: -1.2188

Max Act: 1.1591. Min Act: 0.0000

Data Index: 495413 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 1.2188. Min Range: -1.2188

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1573878 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 1.2188. Min Range: -1.2188

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1304220 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 1.2188. Min Range: -1.2188

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1396136 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1998348 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1399385 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 1.2188. Min Range: -1.2188

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1738128 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.9815. Min Act: -0.0000

Data Index: 332206 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.9205. Min Act: -0.0000

Data Index: 870021 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.9058. Min Act: -0.0000

Data Index: 1196674 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1683119 (The Pile)

Max Activating Token Index: 591

Text #11

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1971805 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.8753. Min Act: -0.0000

Data Index: 43509 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1961723 (The Pile)

Max Activating Token Index: 698

Text #14

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.8408. Min Act: -0.0000

Data Index: 648221 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1990323 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1734713 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1870077 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.8676. Min Act: -0.0000

Data Index: 26406 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 1.2188. Min Range: -1.2188

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1278932 (The Pile)

Max Activating Token Index: 739