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

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

Neuron 322 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: 0.4811. Min Range: -0.4811

Max Act: 0.4718. Min Act: -0.0000

Data Index: 330503 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4811. Min Act: -0.0000

Data Index: 934971 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1302316 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1199803 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4443. Min Act: -0.0000

Data Index: 84194 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1343014 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1243325 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1502831 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1403684 (Python Code)

Max Activating Token Index: 832

Text #9

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1400695 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1394264 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1653733 (Python Code)

Max Activating Token Index: 725

Text #12

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3265. Min Act: -0.0001

Data Index: 1392318 (Python Code)

Max Activating Token Index: 700

Text #13

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2901. Min Act: -0.0000

Data Index: 528690 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1559335 (Python Code)

Max Activating Token Index: 911

Text #15

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1573370 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1510443 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1548663 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1585870 (Python Code)

Max Activating Token Index: 290

Text #19

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1641601 (Python Code)

Max Activating Token Index: 774