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

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

Neuron 2038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1515529 (Python Code)

Max Activating Token Index: 771

Text #1

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1411205 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1513062 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1622638 (Python Code)

Max Activating Token Index: 469

Text #4

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1479042 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1647642 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1591712 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1509750 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1616594 (Python Code)

Max Activating Token Index: 771

Text #9

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1517195 (Python Code)

Max Activating Token Index: 522

Text #10

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1591282 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1431895 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1456116 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1398180 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1390163 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1413956 (Python Code)

Max Activating Token Index: 233

Text #16

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1422330 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1394194 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1561565 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1520185 (Python Code)

Max Activating Token Index: 78