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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3873 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.6714. Min Act: -0.0000

Data Index: 1490453 (Python Code)

Max Activating Token Index: 322

Text #1

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.5499. Min Act: -0.0000

Data Index: 1504763 (Python Code)

Max Activating Token Index: 760

Text #2

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.5409. Min Act: -0.0000

Data Index: 1656927 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.3441. Min Act: -0.0000

Data Index: 1361242 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.3026. Min Act: -0.0000

Data Index: 1488210 (Python Code)

Max Activating Token Index: 304

Text #5

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.2558. Min Act: -0.0000

Data Index: 1507963 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.4093. Min Act: -0.0000

Data Index: 1569981 (Python Code)

Max Activating Token Index: 665

Text #7

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.2798. Min Act: -0.0000

Data Index: 1601601 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 2.6714. Min Range: -2.6714

Max Act: 2.0569. Min Act: -0.0000

Data Index: 1535266 (Python Code)

Max Activating Token Index: 119

Text #9

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.9983. Min Act: -0.0000

Data Index: 1428660 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.7144. Min Act: -0.0000

Data Index: 1393698 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1506889 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.5448. Min Act: -0.0000

Data Index: 1597453 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.4278. Min Act: -0.0000

Data Index: 1606911 (Python Code)

Max Activating Token Index: 895

Text #14

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1393701 (Python Code)

Max Activating Token Index: 515

Text #15

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1412045 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.3612. Min Act: -0.0000

Data Index: 245829 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.3278. Min Act: -0.0000

Data Index: 1558592 (Python Code)

Max Activating Token Index: 782

Text #18

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.3924. Min Act: -0.0000

Data Index: 1582999 (Python Code)

Max Activating Token Index: 729

Text #19

Max Range: 2.6714. Min Range: -2.6714

Max Act: 1.2808. Min Act: -0.0000

Data Index: 1551844 (Python Code)

Max Activating Token Index: 621