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

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

Neuron 3147 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2285. Min Act: -0.0000

Data Index: 194739 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1182636 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2097. Min Act: -0.0000

Data Index: 733392 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2047. Min Act: -0.0000

Data Index: 523549 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1925. Min Act: -0.0000

Data Index: 695387 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1023432 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1259151 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1219086 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1682. Min Act: -0.0000

Data Index: 854215 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1726. Min Act: -0.0000

Data Index: 67866 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1095446 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1124513 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1217464 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1430830 (Python Code)

Max Activating Token Index: 970

Text #14

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1274656 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1484512 (Python Code)

Max Activating Token Index: 973

Text #16

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1240220 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1472. Min Act: -0.0000

Data Index: 587491 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1598264 (Python Code)

Max Activating Token Index: 727

Text #19

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1596242 (Python Code)

Max Activating Token Index: 73