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

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

Neuron 5704 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.3994. Min Act: 0.0000

Data Index: 1580527 (Python Code)

Max Activating Token Index: 838

Text #1

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1477958 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.1258. Min Act: -0.0000

Data Index: 1521997 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.1684. Min Act: 0.0000

Data Index: 1644432 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.1551. Min Act: 0.0000

Data Index: 1655460 (Python Code)

Max Activating Token Index: 303

Text #5

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1652019 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1580082 (Python Code)

Max Activating Token Index: 156

Text #7

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1561301 (Python Code)

Max Activating Token Index: 238

Text #8

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1539793 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1617050 (Python Code)

Max Activating Token Index: 889

Text #10

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1364060 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.0326. Min Act: 0.0000

Data Index: 1399398 (Python Code)

Max Activating Token Index: 564

Text #12

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9481. Min Act: 0.0000

Data Index: 1422231 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1431222 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.0060. Min Act: 0.0000

Data Index: 1593352 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1505505 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 1.3994. Min Range: -1.3994

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1581948 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9936. Min Act: 0.0000

Data Index: 1500036 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9213. Min Act: 0.0000

Data Index: 1518797 (Python Code)

Max Activating Token Index: 753

Text #19

Max Range: 1.3994. Min Range: -1.3994

Max Act: 0.9159. Min Act: 0.0000

Data Index: 1480938 (Python Code)

Max Activating Token Index: 884