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

Dataset: The Pile

Neuron 160 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1219158 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.7051. Min Act: -0.0000

Data Index: 578512 (The Pile)

Max Activating Token Index: 55

Text #2

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1753590 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6382. Min Act: -0.0000

Data Index: 605203 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1154794 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1528723 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1433233 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1613284 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5161. Min Act: -0.0000

Data Index: 51213 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1675793 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1372216 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4687. Min Act: -0.0000

Data Index: 771837 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1736636 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1368225 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4794. Min Act: -0.0000

Data Index: 168396 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1916850 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4827. Min Act: -0.0000

Data Index: 134575 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4873. Min Act: -0.0000

Data Index: 435077 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1834614 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1958751 (The Pile)

Max Activating Token Index: 822