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

Dataset: The Pile

Neuron 375 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: 1.0794. Min Range: -1.0794

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1693308 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 1.0794. Min Range: -1.0794

Max Act: 1.0293. Min Act: -0.0000

Data Index: 308051 (The Pile)

Max Activating Token Index: 603

Text #2

Max Range: 1.0794. Min Range: -1.0794

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1573949 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9880. Min Act: -0.0000

Data Index: 991717 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1484273 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1620639 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1745805 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9358. Min Act: -0.0000

Data Index: 22380 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1093523 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1086002 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8583. Min Act: -0.0000

Data Index: 792989 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1859939 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1937358 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8865. Min Act: -0.0000

Data Index: 502670 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8801. Min Act: -0.0000

Data Index: 901987 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1189777 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1210764 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1270880 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8968. Min Act: -0.0000

Data Index: 790221 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7788. Min Act: 0.0000

Data Index: 1306548 (The Pile)

Max Activating Token Index: 781