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

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

Neuron 3140 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1635. Min Act: -0.0000

Data Index: 1300735 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0816. Min Act: -0.0000

Data Index: 439651 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1577557 (Python Code)

Max Activating Token Index: 749

Text #3

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1307396 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1212. Min Act: -0.0000

Data Index: 739313 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1520637 (Python Code)

Max Activating Token Index: 611

Text #6

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1647118 (Python Code)

Max Activating Token Index: 953

Text #7

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0580. Min Act: -0.0000

Data Index: 713998 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1631587 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1056. Min Act: -0.0000

Data Index: 1600326 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1620006 (Python Code)

Max Activating Token Index: 893

Text #11

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0723. Min Act: -0.0000

Data Index: 1483357 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1591811 (Python Code)

Max Activating Token Index: 920

Text #13

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1380923 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1194642 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1386049 (Python Code)

Max Activating Token Index: 866

Text #16

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0282. Min Act: -0.0000

Data Index: 1387636 (Python Code)

Max Activating Token Index: 584

Text #17

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1075. Min Act: -0.0000

Data Index: 183956 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1348206 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9738. Min Act: -0.0000

Data Index: 1587742 (Python Code)

Max Activating Token Index: 279