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

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

Neuron 932 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: 0.1980. Min Range: -0.1980

Max Act: 0.1972. Min Act: -0.0000

Data Index: 879721 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1963. Min Act: -0.0000

Data Index: 893100 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1182149 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1910. Min Act: -0.0000

Data Index: 536322 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1141526 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1092028 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1563187 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1823. Min Act: -0.0000

Data Index: 55775 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1893. Min Act: -0.0000

Data Index: 250315 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1913. Min Act: -0.0000

Data Index: 15236 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1796. Min Act: -0.0000

Data Index: 793078 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1772. Min Act: -0.0000

Data Index: 497794 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1368970 (Python Code)

Max Activating Token Index: 481

Text #13

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1640519 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1756. Min Act: -0.0000

Data Index: 968893 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1746. Min Act: -0.0000

Data Index: 496707 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1267730 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1065586 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1793. Min Act: -0.0000

Data Index: 348927 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.1980. Min Range: -0.1980

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1477002 (Python Code)

Max Activating Token Index: 242