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

Dataset: The Pile

Neuron 3991 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: 0.4984. Min Range: -0.4984

Max Act: 0.4859. Min Act: -0.0000

Data Index: 141312 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4867. Min Act: -0.0000

Data Index: 713665 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1883714 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1850851 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4704. Min Act: -0.0000

Data Index: 956917 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1192276 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4288. Min Act: -0.0000

Data Index: 702308 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4173. Min Act: -0.0000

Data Index: 673567 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1747789 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4396. Min Act: -0.0000

Data Index: 813298 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1542891 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1340142 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4179. Min Act: 0.0000

Data Index: 690665 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1746367 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4082. Min Act: -0.0000

Data Index: 973944 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1429515 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3917. Min Act: -0.0000

Data Index: 640264 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1710664 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1325357 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.4984. Min Range: -0.4984

Max Act: 0.3553. Min Act: 0.0000

Data Index: 701760 (The Pile)

Max Activating Token Index: 644