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

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

Neuron 465 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1006. Min Range: -1.1006

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1495860 (Python Code)

Max Activating Token Index: 313

Text #1

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.8237. Min Act: -0.0000

Data Index: 246855 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.8188. Min Act: -0.0000

Data Index: 285524 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1150553 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1645365 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1546373 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.8080. Min Act: -0.0000

Data Index: 545201 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1520896 (Python Code)

Max Activating Token Index: 738

Text #8

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.8622. Min Act: -0.0000

Data Index: 993202 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1352798 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7356. Min Act: -0.0000

Data Index: 523291 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1378289 (Python Code)

Max Activating Token Index: 887

Text #12

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7520. Min Act: -0.0000

Data Index: 176973 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7270. Min Act: -0.0000

Data Index: 519266 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1045969 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1005239 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1463723 (Python Code)

Max Activating Token Index: 767

Text #17

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7541. Min Act: -0.0000

Data Index: 563439 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1211637 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7122. Min Act: -0.0000

Data Index: 985362 (C4 (Web Text))

Max Activating Token Index: 984