Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2182 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1110754 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1689333 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7591. Min Act: -0.0000

Data Index: 908232 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1014700 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7742. Min Act: -0.0000

Data Index: 853784 (The Pile)

Max Activating Token Index: 1013

Text #5

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1798378 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1324328 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7057. Min Act: -0.0000

Data Index: 623584 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7209. Min Act: -0.0000

Data Index: 424925 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1405487 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6784. Min Act: -0.0000

Data Index: 297426 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6516. Min Act: -0.0000

Data Index: 562953 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6963. Min Act: -0.0000

Data Index: 900708 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6954. Min Act: -0.0000

Data Index: 394204 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6894. Min Act: -0.0000

Data Index: 133372 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6600. Min Act: -0.0000

Data Index: 80103 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1880940 (The Pile)

Max Activating Token Index: 308

Text #17

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1739760 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1193624 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1890721 (The Pile)

Max Activating Token Index: 778