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

Dataset: The Pile

Neuron 312 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: 0.9891. Min Range: -0.9891

Max Act: 0.9592. Min Act: -0.0000

Data Index: 733842 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9891. Min Act: -0.0000

Data Index: 858855 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1137185 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7936. Min Act: -0.0000

Data Index: 844064 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7305. Min Act: -0.0000

Data Index: 831887 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1972958 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1681035 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7079. Min Act: -0.0000

Data Index: 880547 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6322. Min Act: -0.0000

Data Index: 105743 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6813. Min Act: -0.0000

Data Index: 159172 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6320. Min Act: -0.0000

Data Index: 760206 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6203. Min Act: -0.0000

Data Index: 601380 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6184. Min Act: -0.0000

Data Index: 941878 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1825240 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.5862. Min Act: -0.0000

Data Index: 916038 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6103. Min Act: -0.0000

Data Index: 893413 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6266. Min Act: -0.0000

Data Index: 417138 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6073. Min Act: -0.0000

Data Index: 704009 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1011422 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1117089 (The Pile)

Max Activating Token Index: 158