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

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

Neuron 1104 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0783. Min Range: -1.0783

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1505308 (Python Code)

Max Activating Token Index: 496

Text #1

Max Range: 1.0783. Min Range: -1.0783

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1496063 (Python Code)

Max Activating Token Index: 792

Text #2

Max Range: 1.0783. Min Range: -1.0783

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1383440 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1598210 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1493382 (Python Code)

Max Activating Token Index: 578

Text #5

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1511616 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1628206 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1429441 (Python Code)

Max Activating Token Index: 760

Text #8

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1494837 (Python Code)

Max Activating Token Index: 475

Text #9

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1461139 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1586644 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1479167 (Python Code)

Max Activating Token Index: 657

Text #12

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1617660 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1472147 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1423354 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1533988 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1582330 (Python Code)

Max Activating Token Index: 909

Text #17

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1394346 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1390171 (Python Code)

Max Activating Token Index: 868

Text #19

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1429419 (Python Code)

Max Activating Token Index: 43