Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1502 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1601. Min Range: -1.1601

Max Act: 1.1601. Min Act: -0.0000

Data Index: 394038 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9749. Min Act: -0.0000

Data Index: 917794 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9962. Min Act: -0.0001

Data Index: 785069 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.7504. Min Act: -0.0000

Data Index: 863285 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1126889 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.7336. Min Act: -0.0000

Data Index: 97849 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.7324. Min Act: -0.0000

Data Index: 788262 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1094687 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1222131 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1085686 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6782. Min Act: -0.0000

Data Index: 968446 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6738. Min Act: -0.0000

Data Index: 316360 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1057020 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6683. Min Act: -0.0000

Data Index: 639567 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6544. Min Act: -0.0000

Data Index: 757883 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6418. Min Act: -0.0000

Data Index: 870779 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6128. Min Act: -0.0000

Data Index: 314224 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1342016 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1186768 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1191679 (C4 (Web Text))

Max Activating Token Index: 251