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

Dataset: The Pile

Neuron 869 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.5599. Min Act: -0.0000

Data Index: 338952 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1715267 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4797. Min Act: -0.0000

Data Index: 249107 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4743. Min Act: -0.0000

Data Index: 618290 (The Pile)

Max Activating Token Index: 67

Text #4

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1276654 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1549342 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4927. Min Act: -0.0000

Data Index: 851792 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1316287 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1621988 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1543024 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1843019 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1716654 (The Pile)

Max Activating Token Index: 828

Text #12

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4045. Min Act: -0.0000

Data Index: 165423 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4018. Min Act: -0.0000

Data Index: 36378 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3866. Min Act: -0.0000

Data Index: 759338 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3955. Min Act: -0.0000

Data Index: 116011 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1819152 (The Pile)

Max Activating Token Index: 844

Text #17

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4064. Min Act: -0.0000

Data Index: 450029 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1903261 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1223241 (The Pile)

Max Activating Token Index: 990