Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2691 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1794. Min Act: -0.0001

Data Index: 42363 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1628. Min Act: -0.0001

Data Index: 70493 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1610. Min Act: -0.0000

Data Index: 987703 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1059380 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1445. Min Act: 0.0000

Data Index: 1010454 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1442. Min Act: -0.0001

Data Index: 3820 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1326. Min Act: -0.0001

Data Index: 717363 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1268. Min Act: 0.0000

Data Index: 498658 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1322. Min Act: -0.0001

Data Index: 767352 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1275. Min Act: -0.0001

Data Index: 849490 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1254. Min Act: -0.0001

Data Index: 967443 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1228. Min Act: -0.0001

Data Index: 545910 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1235. Min Act: -0.0001

Data Index: 16135 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1182. Min Act: -0.0001

Data Index: 719599 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1159. Min Act: 0.0000

Data Index: 1351839 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1204. Min Act: 0.0000

Data Index: 1022139 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1236. Min Act: -0.0001

Data Index: 35984 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1130. Min Act: -0.0001

Data Index: 613846 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1116. Min Act: 0.0000

Data Index: 956230 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1086. Min Act: -0.0001

Data Index: 725751 (C4 (Web Text))

Max Activating Token Index: 822