Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3028 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7737. Min Act: -0.0000

Data Index: 784867 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7881. Min Act: -0.0000

Data Index: 883528 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7661. Min Act: -0.0000

Data Index: 543950 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1176233 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6834. Min Act: -0.0001

Data Index: 1049210 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7048. Min Act: -0.0000

Data Index: 208272 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6648. Min Act: -0.0000

Data Index: 223877 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6620. Min Act: -0.0001

Data Index: 983991 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6747. Min Act: -0.0001

Data Index: 174183 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6498. Min Act: -0.0001

Data Index: 1351436 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6733. Min Act: -0.0001

Data Index: 1232443 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6294. Min Act: -0.0000

Data Index: 859523 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6503. Min Act: -0.0000

Data Index: 714859 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6930. Min Act: -0.0001

Data Index: 244875 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1090350 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6291. Min Act: -0.0000

Data Index: 233149 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6269. Min Act: -0.0000

Data Index: 773688 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6089. Min Act: -0.0000

Data Index: 627759 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6408. Min Act: -0.0000

Data Index: 865885 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6541. Min Act: -0.0000

Data Index: 947665 (C4 (Web Text))

Max Activating Token Index: 227