Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 746 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.2251. Min Act: -0.0000

Data Index: 878722 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.2149. Min Act: -0.0000

Data Index: 785023 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.2154. Min Act: -0.0000

Data Index: 553379 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1065. Min Act: -0.0000

Data Index: 466085 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1050. Min Act: -0.0000

Data Index: 58526 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.2104. Min Act: -0.0000

Data Index: 1283583 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1211. Min Act: -0.0000

Data Index: 812706 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1202. Min Act: -0.0000

Data Index: 19291 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1979. Min Act: -0.0000

Data Index: 122817 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1188397 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1233557 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1059. Min Act: -0.0000

Data Index: 142909 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1122985 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.0328. Min Act: -0.0000

Data Index: 431617 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1411. Min Act: -0.0000

Data Index: 185834 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1396. Min Act: -0.0000

Data Index: 979763 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.0980. Min Act: -0.0000

Data Index: 694177 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.0225. Min Act: -0.0000

Data Index: 874749 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.1019. Min Act: -0.0000

Data Index: 251733 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 1.2251. Min Range: -1.2251

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1182572 (C4 (Web Text))

Max Activating Token Index: 75