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

Dataset: The Pile

Neuron 2161 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.9955. Min Act: -0.0000

Data Index: 957512 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.3967. Min Act: -0.0000

Data Index: 1188617 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 3.9955. Min Range: -3.9955

Max Act: 2.9873. Min Act: -0.0000

Data Index: 1024612 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0859. Min Act: -0.0000

Data Index: 1125467 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.3666. Min Act: -0.0000

Data Index: 184722 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.2006. Min Act: -0.0000

Data Index: 181421 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0014. Min Act: -0.0000

Data Index: 1828028 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0262. Min Act: -0.0000

Data Index: 1903909 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0742. Min Act: -0.0000

Data Index: 617967 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0798. Min Act: -0.0000

Data Index: 188012 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0439. Min Act: -0.0000

Data Index: 1543273 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0267. Min Act: -0.0000

Data Index: 17461 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.1738. Min Act: -0.0000

Data Index: 674235 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0085. Min Act: -0.0000

Data Index: 1210742 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 3.9955. Min Range: -3.9955

Max Act: 2.9980. Min Act: -0.0000

Data Index: 155732 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 3.9955. Min Range: -3.9955

Max Act: 3.0103. Min Act: -0.0000

Data Index: 1577620 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 3.9955. Min Range: -3.9955

Max Act: 2.9801. Min Act: -0.0000

Data Index: 481653 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 3.9955. Min Range: -3.9955

Max Act: 2.9748. Min Act: -0.0000

Data Index: 777780 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 3.9955. Min Range: -3.9955

Max Act: 2.9712. Min Act: -0.0000

Data Index: 1365047 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 3.9955. Min Range: -3.9955

Max Act: 2.9593. Min Act: -0.0000

Data Index: 1140437 (The Pile)

Max Activating Token Index: 37