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

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

Neuron 5379 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.5280. Min Act: -0.0001

Data Index: 1592566 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3010. Min Act: -0.0001

Data Index: 1528312 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.0314. Min Act: -0.0001

Data Index: 1413492 (Python Code)

Max Activating Token Index: 845

Text #3

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.1946. Min Act: -0.0001

Data Index: 1613161 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.0199. Min Act: -0.0001

Data Index: 1364276 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2873. Min Act: -0.0001

Data Index: 1605605 (Python Code)

Max Activating Token Index: 205

Text #6

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2905. Min Act: -0.0001

Data Index: 1569832 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.9221. Min Act: -0.0001

Data Index: 1640462 (Python Code)

Max Activating Token Index: 410

Text #8

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.1128. Min Act: -0.0001

Data Index: 1625801 (Python Code)

Max Activating Token Index: 523

Text #9

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.7976. Min Act: -0.0000

Data Index: 1425259 (Python Code)

Max Activating Token Index: 273

Text #10

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.8635. Min Act: -0.0001

Data Index: 1642221 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.9728. Min Act: -0.0001

Data Index: 1463140 (Python Code)

Max Activating Token Index: 130

Text #12

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.7874. Min Act: -0.0001

Data Index: 1365698 (Python Code)

Max Activating Token Index: 674

Text #13

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.7681. Min Act: -0.0000

Data Index: 1362219 (Python Code)

Max Activating Token Index: 298

Text #14

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.6025. Min Act: -0.0001

Data Index: 1589016 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.4142. Min Act: -0.0001

Data Index: 1534620 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.7906. Min Act: -0.0001

Data Index: 1514146 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.5070. Min Act: -0.0000

Data Index: 1491128 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.6269. Min Act: -0.0001

Data Index: 1484760 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 3.5280. Min Range: -3.5280

Max Act: 2.6262. Min Act: -0.0000

Data Index: 1631350 (Python Code)

Max Activating Token Index: 414