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

Dataset: The Pile

Neuron 411 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1080037 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1944705 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.7265. Min Act: -0.0000

Data Index: 264480 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1430684 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6725. Min Act: -0.0000

Data Index: 984498 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1736113 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1221814 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6389. Min Act: 0.0000

Data Index: 600688 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6284. Min Act: -0.0000

Data Index: 881736 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6569. Min Act: -0.0000

Data Index: 932900 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5781. Min Act: 0.0000

Data Index: 1792680 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1302437 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1555923 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5868. Min Act: -0.0000

Data Index: 527012 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1503827 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1556131 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.6135. Min Act: -0.0000

Data Index: 659318 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5960. Min Act: -0.0000

Data Index: 210349 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1089091 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.5481. Min Act: -0.0000

Data Index: 207681 (The Pile)

Max Activating Token Index: 554