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

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

Neuron 1454 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.1551. Min Act: 0.0000

Data Index: 1374723 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0632. Min Act: 0.0001

Data Index: 1506528 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 1.1551. Min Range: -1.1551

Max Act: 1.0269. Min Act: 0.0001

Data Index: 1615271 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9621. Min Act: 0.0002

Data Index: 1450512 (Python Code)

Max Activating Token Index: 1013

Text #4

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1546850 (Python Code)

Max Activating Token Index: 757

Text #5

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9884. Min Act: 0.0000

Data Index: 1443175 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8794. Min Act: 0.0001

Data Index: 1553428 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8982. Min Act: 0.0002

Data Index: 1569750 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.9036. Min Act: 0.0001

Data Index: 1436896 (Python Code)

Max Activating Token Index: 141

Text #9

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1523599 (Python Code)

Max Activating Token Index: 704

Text #10

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8567. Min Act: 0.0001

Data Index: 1400436 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8530. Min Act: 0.0002

Data Index: 1615515 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1434092 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.7288. Min Act: 0.0001

Data Index: 1514925 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1462230 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8132. Min Act: 0.0002

Data Index: 1495744 (Python Code)

Max Activating Token Index: 638

Text #16

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8271. Min Act: 0.0001

Data Index: 1542423 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1573348 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.8032. Min Act: 0.0000

Data Index: 1529297 (Python Code)

Max Activating Token Index: 223

Text #19

Max Range: 1.1551. Min Range: -1.1551

Max Act: 0.7778. Min Act: 0.0002

Data Index: 1556241 (Python Code)

Max Activating Token Index: 236