Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3652 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1618586 (Python Code)

Max Activating Token Index: 510

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0597. Min Act: -0.0002

Data Index: 972464 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0565. Min Act: -0.0002

Data Index: 563904 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0002

Data Index: 27864 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1373040 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1462573 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0550. Min Act: -0.0003

Data Index: 500326 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0526. Min Act: -0.0002

Data Index: 464853 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1418649 (Python Code)

Max Activating Token Index: 422

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1021012 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1651947 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0525. Min Act: -0.0002

Data Index: 40938 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1514747 (Python Code)

Max Activating Token Index: 87

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1464607 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1401396 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1570033 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0530. Min Act: -0.0002

Data Index: 343369 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0487. Min Act: -0.0003

Data Index: 178124 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1464065 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1433908 (Python Code)

Max Activating Token Index: 113