Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1104 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.7481. Min Act: -0.0000

Data Index: 801451 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.5049. Min Act: -0.0000

Data Index: 1146944 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.5321. Min Act: -0.0000

Data Index: 140453 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.0051. Min Act: -0.0000

Data Index: 1083944 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.0892. Min Act: -0.0000

Data Index: 995723 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 5.7481. Min Range: -5.7481

Max Act: 5.1850. Min Act: -0.0000

Data Index: 1098264 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 5.7481. Min Range: -5.7481

Max Act: 3.0864. Min Act: -0.0000

Data Index: 111783 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 5.7481. Min Range: -5.7481

Max Act: 2.3340. Min Act: -0.0000

Data Index: 1161058 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1253326 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.4244. Min Act: -0.0000

Data Index: 899631 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.2611. Min Act: -0.0000

Data Index: 815513 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1568258 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1367046 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.2440. Min Act: -0.0000

Data Index: 498733 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.1837. Min Act: -0.0000

Data Index: 1563848 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.2104. Min Act: -0.0000

Data Index: 57259 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.1760. Min Act: -0.0000

Data Index: 247806 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1193554 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.2386. Min Act: -0.0000

Data Index: 41753 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 5.7481. Min Range: -5.7481

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1122782 (C4 (Web Text))

Max Activating Token Index: 39