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

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

Neuron 2666 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.0001

Data Index: 1217593 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2647. Min Act: -0.0001

Data Index: 759686 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.1546. Min Act: -0.0000

Data Index: 845504 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.1326. Min Act: -0.0001

Data Index: 836695 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.0925. Min Act: -0.0001

Data Index: 161569 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.0172. Min Act: -0.0001

Data Index: 1002257 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.0185. Min Act: -0.0001

Data Index: 519143 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.9790. Min Act: -0.0001

Data Index: 1074688 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.0036. Min Act: -0.0001

Data Index: 355513 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.9095. Min Act: -0.0001

Data Index: 1051487 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.9882. Min Act: -0.0001

Data Index: 1202558 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.8513. Min Act: -0.0001

Data Index: 166250 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.9182. Min Act: -0.0000

Data Index: 749506 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.8763. Min Act: -0.0001

Data Index: 41059 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.9133. Min Act: -0.0001

Data Index: 309952 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.9233. Min Act: -0.0001

Data Index: 555925 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.8092. Min Act: -0.0001

Data Index: 494499 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.8235. Min Act: -0.0001

Data Index: 205308 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.8142. Min Act: -0.0000

Data Index: 651396 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.2950. Min Range: -1.2950

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1308408 (C4 (Web Text))

Max Activating Token Index: 858