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

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

Neuron 4089 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2332. Min Act: -0.0000

Data Index: 792270 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2066. Min Act: -0.0000

Data Index: 712990 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2084. Min Act: -0.0000

Data Index: 30166 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1756. Min Act: -0.0000

Data Index: 467866 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1701. Min Act: -0.0000

Data Index: 633660 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1758. Min Act: -0.0000

Data Index: 368284 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1423871 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1676. Min Act: -0.0000

Data Index: 563146 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1584. Min Act: -0.0000

Data Index: 819949 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1246735 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1669. Min Act: -0.0000

Data Index: 474344 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1615. Min Act: -0.0000

Data Index: 803958 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1365718 (Python Code)

Max Activating Token Index: 94

Text #13

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1695. Min Act: -0.0000

Data Index: 717663 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1702. Min Act: -0.0000

Data Index: 641737 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1562. Min Act: -0.0000

Data Index: 128844 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1513. Min Act: -0.0000

Data Index: 880015 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1518. Min Act: -0.0000

Data Index: 598624 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1504468 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1463. Min Act: -0.0000

Data Index: 964073 (C4 (Web Text))

Max Activating Token Index: 722