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

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

Neuron 2716 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: 0.7976. Min Range: -0.7976

Max Act: 0.7976. Min Act: -0.0001

Data Index: 375289 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7607. Min Act: -0.0001

Data Index: 370853 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7474. Min Act: -0.0001

Data Index: 273538 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6874. Min Act: -0.0001

Data Index: 79172 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7376. Min Act: -0.0001

Data Index: 1048531 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6806. Min Act: -0.0001

Data Index: 351190 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6959. Min Act: -0.0001

Data Index: 58151 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6421. Min Act: -0.0001

Data Index: 419748 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6608. Min Act: -0.0001

Data Index: 302746 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7007. Min Act: -0.0001

Data Index: 455703 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6537. Min Act: -0.0001

Data Index: 700284 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6671. Min Act: -0.0001

Data Index: 23007 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6958. Min Act: -0.0001

Data Index: 871893 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6559. Min Act: -0.0001

Data Index: 189191 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6262. Min Act: -0.0001

Data Index: 382247 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6219. Min Act: -0.0001

Data Index: 661070 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6240. Min Act: -0.0001

Data Index: 52086 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6359. Min Act: -0.0001

Data Index: 1315703 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6390. Min Act: -0.0001

Data Index: 916483 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6327. Min Act: -0.0001

Data Index: 703788 (C4 (Web Text))

Max Activating Token Index: 991