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

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

Neuron 4784 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1611480 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1472102 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0679. Min Act: -0.0000

Data Index: 911071 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0645. Min Act: -0.0000

Data Index: 605142 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0638. Min Act: -0.0000

Data Index: 867414 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1557205 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0583. Min Act: -0.0000

Data Index: 554561 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0585. Min Act: -0.0000

Data Index: 355850 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1104634 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0571. Min Act: -0.0000

Data Index: 506552 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1510426 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1098052 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1519972 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1421718 (Python Code)

Max Activating Token Index: 725

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1583420 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0536. Min Act: -0.0000

Data Index: 412504 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1104284 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1364806 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0465. Min Act: -0.0000

Data Index: 849804 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1509060 (Python Code)

Max Activating Token Index: 585