Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1625 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4896. Min Act: -0.0001

Data Index: 1640424 (Python Code)

Max Activating Token Index: 309

Text #1

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4404. Min Act: -0.0001

Data Index: 1374491 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4181. Min Act: -0.0001

Data Index: 1530077 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1462718 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4428. Min Act: -0.0001

Data Index: 1640702 (Python Code)

Max Activating Token Index: 138

Text #5

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1504078 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4195. Min Act: -0.0001

Data Index: 1443339 (Python Code)

Max Activating Token Index: 198

Text #7

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4098. Min Act: -0.0001

Data Index: 1404001 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3912. Min Act: -0.0001

Data Index: 1438433 (Python Code)

Max Activating Token Index: 849

Text #9

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4413. Min Act: -0.0001

Data Index: 1578532 (Python Code)

Max Activating Token Index: 138

Text #10

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3895. Min Act: -0.0001

Data Index: 1397622 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4171. Min Act: -0.0001

Data Index: 1496069 (Python Code)

Max Activating Token Index: 167

Text #12

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3876. Min Act: -0.0001

Data Index: 1509377 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3495. Min Act: -0.0001

Data Index: 1631482 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4007. Min Act: -0.0001

Data Index: 1540493 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3861. Min Act: -0.0001

Data Index: 1379567 (Python Code)

Max Activating Token Index: 803

Text #16

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3891. Min Act: -0.0001

Data Index: 1494718 (Python Code)

Max Activating Token Index: 538

Text #17

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4141. Min Act: -0.0001

Data Index: 1426977 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3579. Min Act: -0.0001

Data Index: 1575971 (Python Code)

Max Activating Token Index: 267

Text #19

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4037. Min Act: -0.0001

Data Index: 1373095 (Python Code)

Max Activating Token Index: 50