Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3006 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1936. Min Act: -0.0001

Data Index: 802201 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1920. Min Act: -0.0001

Data Index: 1034159 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1669. Min Act: -0.0001

Data Index: 417640 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1662. Min Act: -0.0001

Data Index: 673196 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1719. Min Act: -0.0001

Data Index: 853722 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1537. Min Act: -0.0001

Data Index: 306269 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1509. Min Act: -0.0001

Data Index: 142458 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1150874 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1545. Min Act: -0.0001

Data Index: 253352 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1662. Min Act: -0.0001

Data Index: 454504 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1587. Min Act: -0.0001

Data Index: 166430 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1381. Min Act: -0.0001

Data Index: 222724 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1527. Min Act: -0.0001

Data Index: 964838 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1568. Min Act: -0.0001

Data Index: 694264 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1741. Min Act: -0.0001

Data Index: 629630 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1545. Min Act: -0.0001

Data Index: 699895 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1539. Min Act: -0.0001

Data Index: 89788 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1555. Min Act: -0.0001

Data Index: 695720 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1551. Min Act: -0.0001

Data Index: 866372 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.1936. Min Range: -0.1936

Max Act: 0.1559. Min Act: -0.0001

Data Index: 785247 (C4 (Web Text))

Max Activating Token Index: 833