Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 682 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0742. Min Act: -0.0001

Data Index: 888572 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1066170 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0710. Min Act: -0.0001

Data Index: 292529 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0656. Min Act: -0.0001

Data Index: 979491 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1017860 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0629. Min Act: -0.0001

Data Index: 35824 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0633. Min Act: -0.0001

Data Index: 916754 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1177102 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0543. Min Act: -0.0001

Data Index: 291888 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1038977 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1034034 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1175031 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0543. Min Act: -0.0001

Data Index: 15705 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0612. Min Act: -0.0001

Data Index: 378150 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0559. Min Act: -0.0001

Data Index: 949855 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1082954 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0547. Min Act: -0.0001

Data Index: 553425 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0525. Min Act: -0.0001

Data Index: 520557 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0567. Min Act: -0.0001

Data Index: 692780 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1405803 (Python Code)

Max Activating Token Index: 685