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

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

Neuron 2875 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.8642. Min Act: -0.0000

Data Index: 1615777 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1628566 (Python Code)

Max Activating Token Index: 171

Text #2

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.4428. Min Act: -0.0000

Data Index: 1528236 (Python Code)

Max Activating Token Index: 300

Text #3

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.5090. Min Act: -0.0000

Data Index: 1452575 (Python Code)

Max Activating Token Index: 918

Text #4

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.4982. Min Act: -0.0000

Data Index: 1428427 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.4414. Min Act: -0.0000

Data Index: 1638515 (Python Code)

Max Activating Token Index: 618

Text #6

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1642974 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1393373 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.4067. Min Act: -0.0000

Data Index: 1574248 (Python Code)

Max Activating Token Index: 587

Text #9

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.3207. Min Act: -0.0000

Data Index: 1524460 (Python Code)

Max Activating Token Index: 573

Text #10

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1361571 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.3496. Min Act: -0.0000

Data Index: 1372098 (Python Code)

Max Activating Token Index: 641

Text #12

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1458813 (Python Code)

Max Activating Token Index: 626

Text #13

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.3118. Min Act: -0.0000

Data Index: 1561223 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1442466 (Python Code)

Max Activating Token Index: 202

Text #15

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1401327 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1445901 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1427460 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1490414 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 1.8642. Min Range: -1.8642

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1392841 (Python Code)

Max Activating Token Index: 549