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

Dataset: The Pile

Neuron 632 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: 0.8908. Min Range: -0.8908

Max Act: 0.8524. Min Act: -0.0000

Data Index: 880202 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1843029 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1320824 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8908. Min Act: -0.0000

Data Index: 153296 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8230. Min Act: -0.0000

Data Index: 837601 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1951811 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1642378 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1916793 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8213. Min Act: -0.0000

Data Index: 643130 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1892156 (The Pile)

Max Activating Token Index: 735

Text #10

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7737. Min Act: -0.0000

Data Index: 579323 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7437. Min Act: -0.0000

Data Index: 722565 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7879. Min Act: -0.0000

Data Index: 277831 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1688160 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7552. Min Act: -0.0000

Data Index: 923527 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1592493 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7342. Min Act: -0.0000

Data Index: 316256 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7806. Min Act: -0.0000

Data Index: 411106 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1080239 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 0.8908. Min Range: -0.8908

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1049846 (The Pile)

Max Activating Token Index: 768