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

Dataset: The Pile

Neuron 83 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: 0.2797. Min Range: -0.2797

Max Act: 0.2797. Min Act: -0.0000

Data Index: 526868 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2434. Min Act: 0.0000

Data Index: 1353713 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1235831 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1973. Min Act: -0.0000

Data Index: 504234 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1881. Min Act: 0.0000

Data Index: 706377 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1680. Min Act: 0.0000

Data Index: 1373727 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1513574 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1865. Min Act: -0.0000

Data Index: 595905 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1116859 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1688. Min Act: -0.0000

Data Index: 126791 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1553. Min Act: -0.0000

Data Index: 915191 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1586. Min Act: 0.0000

Data Index: 1163747 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1039312 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1898096 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1322011 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1590. Min Act: -0.0000

Data Index: 128112 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1442. Min Act: -0.0000

Data Index: 895481 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1545. Min Act: 0.0000

Data Index: 120148 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1770858 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1551845 (The Pile)

Max Activating Token Index: 433