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

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

Neuron 3670 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1575055 (Python Code)

Max Activating Token Index: 147

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0643. Min Act: -0.0000

Data Index: 934390 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0642. Min Act: -0.0001

Data Index: 788645 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0611. Min Act: -0.0000

Data Index: 276276 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1255868 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1634543 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0583. Min Act: -0.0000

Data Index: 677547 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0537. Min Act: -0.0000

Data Index: 316780 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1627551 (Python Code)

Max Activating Token Index: 453

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1150196 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0561. Min Act: -0.0000

Data Index: 523813 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0557. Min Act: -0.0000

Data Index: 24850 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0578. Min Act: -0.0000

Data Index: 85845 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1033024 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1271120 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0546. Min Act: -0.0000

Data Index: 854042 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1281881 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1283382 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0534. Min Act: -0.0000

Data Index: 237392 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0573. Min Act: -0.0000

Data Index: 354959 (C4 (Web Text))

Max Activating Token Index: 164