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

Dataset: The Pile

Neuron 4856 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.6479. Min Act: -0.0000

Data Index: 1504184 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 4.2767. Min Range: -4.2767

Max Act: 4.2767. Min Act: -0.0000

Data Index: 1146395 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.8130. Min Act: -0.0000

Data Index: 1591419 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.9499. Min Act: -0.0000

Data Index: 1037147 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 4.2767. Min Range: -4.2767

Max Act: 4.2038. Min Act: -0.0000

Data Index: 237661 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.9165. Min Act: -0.0000

Data Index: 1641676 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.5899. Min Act: -0.0000

Data Index: 806215 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.7728. Min Act: -0.0000

Data Index: 722962 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.4894. Min Act: -0.0000

Data Index: 672006 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.6410. Min Act: -0.0000

Data Index: 332020 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.5298. Min Act: -0.0000

Data Index: 1901158 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.4325. Min Act: -0.0000

Data Index: 196419 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.4714. Min Act: -0.0000

Data Index: 332016 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.4038. Min Act: -0.0000

Data Index: 63767 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.0701. Min Act: -0.0000

Data Index: 1860362 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.0390. Min Act: -0.0000

Data Index: 1584514 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.0973. Min Act: -0.0000

Data Index: 1072299 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.0607. Min Act: 0.0002

Data Index: 720944 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 4.2767. Min Range: -4.2767

Max Act: 1.9861. Min Act: 0.0000

Data Index: 113855 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 4.2767. Min Range: -4.2767

Max Act: 1.8898. Min Act: -0.0000

Data Index: 863533 (The Pile)

Max Activating Token Index: 246