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

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

Neuron 4349 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: 1.9776. Min Range: -1.9776

Max Act: 1.9776. Min Act: -0.0000

Data Index: 1600897 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.6997. Min Act: -0.0000

Data Index: 1393362 (Python Code)

Max Activating Token Index: 60

Text #2

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1412520 (Python Code)

Max Activating Token Index: 345

Text #3

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.5110. Min Act: -0.0000

Data Index: 1401840 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1447343 (Python Code)

Max Activating Token Index: 651

Text #5

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.5655. Min Act: -0.0000

Data Index: 1474658 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1581461 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1458774 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1653623 (Python Code)

Max Activating Token Index: 543

Text #9

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4964. Min Act: -0.0000

Data Index: 1521943 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1436179 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4513. Min Act: -0.0000

Data Index: 1511826 (Python Code)

Max Activating Token Index: 679

Text #12

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4326. Min Act: -0.0000

Data Index: 1534803 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1364399 (Python Code)

Max Activating Token Index: 653

Text #14

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4076. Min Act: -0.0000

Data Index: 1570080 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1558125 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1591252 (Python Code)

Max Activating Token Index: 424

Text #17

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1500998 (Python Code)

Max Activating Token Index: 447

Text #18

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.3813. Min Act: -0.0000

Data Index: 1566759 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 1.9776. Min Range: -1.9776

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1480966 (Python Code)

Max Activating Token Index: 957