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

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

Neuron 912 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.8686. Min Act: -0.0000

Data Index: 1317942 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.5984. Min Act: -0.0000

Data Index: 814809 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.4619. Min Act: -0.0000

Data Index: 512178 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.4127. Min Act: -0.0000

Data Index: 681804 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3336. Min Act: -0.0000

Data Index: 766955 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1058665 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3171. Min Act: -0.0000

Data Index: 781381 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3434. Min Act: -0.0000

Data Index: 447212 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1221936 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.2528. Min Act: -0.0000

Data Index: 159146 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.1825. Min Act: -0.0000

Data Index: 1126303 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.2683. Min Act: -0.0000

Data Index: 345754 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1595725 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.1509. Min Act: -0.0000

Data Index: 767764 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.1720. Min Act: -0.0000

Data Index: 1320392 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1590587 (Python Code)

Max Activating Token Index: 748

Text #16

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.1218. Min Act: -0.0000

Data Index: 43724 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.0597. Min Act: -0.0000

Data Index: 1227629 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.0993. Min Act: -0.0000

Data Index: 531144 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 1.8686. Min Range: -1.8686

Max Act: 1.1165. Min Act: -0.0000

Data Index: 90365 (C4 (Web Text))

Max Activating Token Index: 1012