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

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

Neuron 292 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: 1.1010. Min Range: -1.1010

Max Act: 1.1010. Min Act: -0.0000

Data Index: 855722 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8874. Min Act: -0.0000

Data Index: 520811 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9922. Min Act: -0.0000

Data Index: 759080 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1031516 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9557. Min Act: 0.0000

Data Index: 694150 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9430. Min Act: -0.0000

Data Index: 900131 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9194. Min Act: -0.0000

Data Index: 380825 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9378. Min Act: 0.0000

Data Index: 298910 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8845. Min Act: 0.0000

Data Index: 876528 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8531. Min Act: 0.0000

Data Index: 105392 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1107393 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8641. Min Act: -0.0000

Data Index: 778338 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1167712 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8265. Min Act: 0.0000

Data Index: 798719 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8411. Min Act: 0.0000

Data Index: 1335526 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8580. Min Act: 0.0000

Data Index: 482673 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8607. Min Act: -0.0000

Data Index: 880824 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.8408. Min Act: 0.0000

Data Index: 175123 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7676. Min Act: 0.0000

Data Index: 1303641 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.1010. Min Range: -1.1010

Max Act: 0.7815. Min Act: 0.0000

Data Index: 574388 (C4 (Web Text))

Max Activating Token Index: 535