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

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

Neuron 3316 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: 0.8233. Min Range: -0.8233

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1411177 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1438672 (Python Code)

Max Activating Token Index: 951

Text #2

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1592424 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5415. Min Act: -0.0000

Data Index: 597629 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1448766 (Python Code)

Max Activating Token Index: 448

Text #5

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.4014. Min Act: -0.0000

Data Index: 730884 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.4060. Min Act: -0.0000

Data Index: 252731 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3838. Min Act: -0.0000

Data Index: 288140 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1118839 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3718. Min Act: -0.0000

Data Index: 990096 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1105685 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3529. Min Act: -0.0000

Data Index: 469445 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3483. Min Act: -0.0000

Data Index: 946898 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3459. Min Act: -0.0000

Data Index: 846431 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3559. Min Act: -0.0000

Data Index: 39621 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3497. Min Act: -0.0000

Data Index: 204600 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3480. Min Act: -0.0000

Data Index: 567046 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3435. Min Act: -0.0000

Data Index: 713494 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3415. Min Act: -0.0000

Data Index: 971541 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1060672 (C4 (Web Text))

Max Activating Token Index: 722