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

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

Neuron 3706 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1744. Min Range: -2.1744

Max Act: 2.1744. Min Act: -0.0000

Data Index: 44593 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.6418. Min Act: -0.0000

Data Index: 1314252 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1047723 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.4229. Min Act: 0.0000

Data Index: 956939 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.4271. Min Act: -0.0000

Data Index: 62686 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.3373. Min Act: 0.0000

Data Index: 557315 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.3595. Min Act: 0.0000

Data Index: 952917 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.2957. Min Act: -0.0000

Data Index: 169339 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.2111. Min Act: -0.0000

Data Index: 899658 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.2755. Min Act: -0.0000

Data Index: 707264 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1080226 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.2430. Min Act: 0.0000

Data Index: 623572 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.2372. Min Act: 0.0000

Data Index: 302287 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.1564. Min Act: 0.0001

Data Index: 1278291 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.2020. Min Act: 0.0000

Data Index: 1085325 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1271765 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.2562. Min Act: -0.0000

Data Index: 807588 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1119852 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.1563. Min Act: -0.0000

Data Index: 100373 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 2.1744. Min Range: -2.1744

Max Act: 1.1556. Min Act: 0.0001

Data Index: 336195 (C4 (Web Text))

Max Activating Token Index: 423