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

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

Neuron 4110 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3351. Min Range: -3.3351

Max Act: 3.3351. Min Act: -0.0000

Data Index: 273985 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.3351. Min Range: -3.3351

Max Act: 3.0352. Min Act: -0.0000

Data Index: 1244933 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 3.3351. Min Range: -3.3351

Max Act: 3.0507. Min Act: -0.0000

Data Index: 1207896 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 3.3351. Min Range: -3.3351

Max Act: 3.0027. Min Act: -0.0000

Data Index: 1248006 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.8344. Min Act: -0.0000

Data Index: 1108145 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.9171. Min Act: -0.0000

Data Index: 41837 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.9269. Min Act: -0.0000

Data Index: 74544 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.7834. Min Act: -0.0000

Data Index: 35682 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.9028. Min Act: -0.0000

Data Index: 523495 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.7462. Min Act: -0.0000

Data Index: 629586 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.7360. Min Act: -0.0000

Data Index: 471166 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.7088. Min Act: -0.0000

Data Index: 344084 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.7162. Min Act: -0.0000

Data Index: 1124457 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.9801. Min Act: -0.0000

Data Index: 719805 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.5557. Min Act: -0.0000

Data Index: 222634 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.6612. Min Act: -0.0000

Data Index: 1218024 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.8461. Min Act: -0.0000

Data Index: 1357685 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.7993. Min Act: -0.0000

Data Index: 910332 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.7511. Min Act: -0.0000

Data Index: 911764 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 3.3351. Min Range: -3.3351

Max Act: 2.8771. Min Act: -0.0000

Data Index: 658604 (C4 (Web Text))

Max Activating Token Index: 848