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

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

Neuron 1754 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7517. Min Range: -2.7517

Max Act: 2.7517. Min Act: -0.0000

Data Index: 1580036 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 2.7517. Min Range: -2.7517

Max Act: 2.6778. Min Act: -0.0000

Data Index: 1563191 (Python Code)

Max Activating Token Index: 400

Text #2

Max Range: 2.7517. Min Range: -2.7517

Max Act: 2.2938. Min Act: -0.0000

Data Index: 1436574 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 2.7517. Min Range: -2.7517

Max Act: 2.3166. Min Act: -0.0000

Data Index: 1564742 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.9863. Min Act: -0.0000

Data Index: 1615889 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.6954. Min Act: -0.0000

Data Index: 1535149 (Python Code)

Max Activating Token Index: 902

Text #6

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.7090. Min Act: -0.0000

Data Index: 1412700 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.6974. Min Act: -0.0000

Data Index: 1457866 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1393777 (Python Code)

Max Activating Token Index: 203

Text #9

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.5208. Min Act: -0.0000

Data Index: 1494381 (Python Code)

Max Activating Token Index: 84

Text #10

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1574650 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1641785 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1656714 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.5482. Min Act: -0.0000

Data Index: 1588126 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.6070. Min Act: -0.0000

Data Index: 1464280 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1468296 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.4425. Min Act: -0.0000

Data Index: 1584459 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1363106 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1367932 (Python Code)

Max Activating Token Index: 747

Text #19

Max Range: 2.7517. Min Range: -2.7517

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1446906 (Python Code)

Max Activating Token Index: 186