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

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

Neuron 4372 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: 2.1635. Min Range: -2.1635

Max Act: 2.1635. Min Act: -0.0000

Data Index: 1524677 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 2.1635. Min Range: -2.1635

Max Act: 2.0569. Min Act: -0.0000

Data Index: 1530408 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.9354. Min Act: -0.0000

Data Index: 1504946 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.8068. Min Act: -0.0000

Data Index: 1563402 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.6926. Min Act: -0.0000

Data Index: 1614484 (Python Code)

Max Activating Token Index: 770

Text #5

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.9025. Min Act: -0.0000

Data Index: 1469073 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.8748. Min Act: -0.0000

Data Index: 1399643 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.7691. Min Act: -0.0000

Data Index: 1445993 (Python Code)

Max Activating Token Index: 497

Text #8

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.7588. Min Act: -0.0000

Data Index: 1593897 (Python Code)

Max Activating Token Index: 825

Text #9

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.8315. Min Act: -0.0000

Data Index: 1606614 (Python Code)

Max Activating Token Index: 810

Text #10

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.8255. Min Act: -0.0000

Data Index: 1401980 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.9134. Min Act: -0.0000

Data Index: 1361822 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.6576. Min Act: -0.0000

Data Index: 1589784 (Python Code)

Max Activating Token Index: 803

Text #13

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.7503. Min Act: -0.0000

Data Index: 1476053 (Python Code)

Max Activating Token Index: 762

Text #14

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.6366. Min Act: -0.0000

Data Index: 1595797 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.7306. Min Act: -0.0000

Data Index: 1449857 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1603351 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.6156. Min Act: -0.0000

Data Index: 1429186 (Python Code)

Max Activating Token Index: 1010

Text #18

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.6104. Min Act: -0.0000

Data Index: 1567969 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 2.1635. Min Range: -2.1635

Max Act: 1.8107. Min Act: -0.0000

Data Index: 1649456 (Python Code)

Max Activating Token Index: 135