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

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

Neuron 970 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1521836 (Python Code)

Max Activating Token Index: 609

Text #1

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1412906 (Python Code)

Max Activating Token Index: 741

Text #2

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1487201 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1416152 (Python Code)

Max Activating Token Index: 340

Text #4

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1621683 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1518327 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1522879 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1543793 (Python Code)

Max Activating Token Index: 189

Text #8

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1371421 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1544122 (Python Code)

Max Activating Token Index: 65

Text #10

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1435099 (Python Code)

Max Activating Token Index: 790

Text #11

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1371967 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1446781 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1381985 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1626122 (Python Code)

Max Activating Token Index: 611

Text #15

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1544145 (Python Code)

Max Activating Token Index: 243

Text #16

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8202. Min Act: -0.0000

Data Index: 12671 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1595763 (Python Code)

Max Activating Token Index: 718

Text #18

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1612991 (Python Code)

Max Activating Token Index: 513

Text #19

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1541818 (Python Code)

Max Activating Token Index: 278