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

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

Neuron 4145 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: 1.4822. Min Range: -1.4822

Max Act: 1.4822. Min Act: -0.0000

Data Index: 363510 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.3554. Min Act: -0.0000

Data Index: 655967 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.3228. Min Act: -0.0000

Data Index: 420612 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1148715 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2672. Min Act: -0.0000

Data Index: 612371 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2922. Min Act: -0.0001

Data Index: 365833 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.2837. Min Act: -0.0000

Data Index: 687154 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1107624 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1661. Min Act: -0.0000

Data Index: 781102 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0601. Min Act: -0.0000

Data Index: 810315 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1049. Min Act: -0.0000

Data Index: 368445 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1050. Min Act: -0.0000

Data Index: 1169464 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0377. Min Act: -0.0000

Data Index: 657949 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0175. Min Act: -0.0000

Data Index: 891579 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1063. Min Act: -0.0000

Data Index: 649451 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.1818. Min Act: -0.0000

Data Index: 459476 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 1.4822. Min Range: -1.4822

Max Act: 0.9969. Min Act: -0.0000

Data Index: 582458 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0616. Min Act: -0.0000

Data Index: 955833 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0607. Min Act: -0.0001

Data Index: 689481 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.4822. Min Range: -1.4822

Max Act: 1.0678. Min Act: -0.0000

Data Index: 954033 (C4 (Web Text))

Max Activating Token Index: 44