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

Dataset: The Pile

Neuron 2500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8920. Min Act: -0.0000

Data Index: 137127 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8706. Min Act: -0.0000

Data Index: 615470 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7637. Min Act: -0.0000

Data Index: 29524 (The Pile)

Max Activating Token Index: 207

Text #3

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8065. Min Act: -0.0000

Data Index: 832500 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1477704 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7291. Min Act: -0.0000

Data Index: 943102 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7880. Min Act: -0.0000

Data Index: 825945 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6190. Min Act: -0.0000

Data Index: 543984 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1788196 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7364. Min Act: -0.0000

Data Index: 141210 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6887. Min Act: -0.0000

Data Index: 574597 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1371380 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6499. Min Act: -0.0000

Data Index: 349948 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1200620 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1279114 (The Pile)

Max Activating Token Index: 780

Text #15

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1731010 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1316071 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6607. Min Act: -0.0000

Data Index: 890553 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1665849 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1071556 (The Pile)

Max Activating Token Index: 570