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

Dataset: The Pile

Neuron 3416 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1400340 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1113285 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1926300 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1132457 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7281. Min Act: -0.0000

Data Index: 896346 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7058. Min Act: -0.0000

Data Index: 842200 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7745. Min Act: -0.0000

Data Index: 136750 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7177. Min Act: -0.0000

Data Index: 97620 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6917. Min Act: -0.0000

Data Index: 685318 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6714. Min Act: -0.0000

Data Index: 15264 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1145085 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1651371 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1653545 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7005. Min Act: -0.0000

Data Index: 848490 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6767. Min Act: -0.0000

Data Index: 547447 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6889. Min Act: -0.0000

Data Index: 871600 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1366787 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1584272 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6816. Min Act: -0.0000

Data Index: 357823 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1558170 (The Pile)

Max Activating Token Index: 816