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

Dataset: The Pile

Neuron 4664 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.5259. Min Act: -0.0000

Data Index: 1795616 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.2048. Min Act: -0.0000

Data Index: 122617 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.1115. Min Act: -0.0000

Data Index: 535816 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.1954. Min Act: -0.0000

Data Index: 1668239 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0999. Min Act: -0.0000

Data Index: 569977 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1766017 (The Pile)

Max Activating Token Index: 291

Text #6

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0922. Min Act: -0.0000

Data Index: 888049 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0644. Min Act: -0.0000

Data Index: 644448 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1365461 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1818775 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.9756. Min Act: -0.0000

Data Index: 305818 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1785019 (The Pile)

Max Activating Token Index: 910

Text #12

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0209. Min Act: -0.0000

Data Index: 394820 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0023. Min Act: -0.0000

Data Index: 730992 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0225. Min Act: -0.0000

Data Index: 593989 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1771348 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1278687 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1938984 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.5259. Min Range: -1.5259

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1490480 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 1.5259. Min Range: -1.5259

Max Act: 0.9984. Min Act: -0.0000

Data Index: 158797 (The Pile)

Max Activating Token Index: 559