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

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

Neuron 3731 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4814. Min Range: -3.4814

Max Act: 3.4631. Min Act: -0.0000

Data Index: 1408604 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 3.4814. Min Range: -3.4814

Max Act: 3.4814. Min Act: -0.0000

Data Index: 1364390 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 3.4814. Min Range: -3.4814

Max Act: 2.9790. Min Act: -0.0000

Data Index: 1562790 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 3.4814. Min Range: -3.4814

Max Act: 3.0356. Min Act: -0.0000

Data Index: 1645261 (Python Code)

Max Activating Token Index: 719

Text #4

Max Range: 3.4814. Min Range: -3.4814

Max Act: 2.8649. Min Act: -0.0000

Data Index: 1479865 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 3.4814. Min Range: -3.4814

Max Act: 2.3907. Min Act: -0.0000

Data Index: 1474938 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 3.4814. Min Range: -3.4814

Max Act: 2.2624. Min Act: -0.0000

Data Index: 1589631 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 3.4814. Min Range: -3.4814

Max Act: 2.3777. Min Act: -0.0000

Data Index: 1506869 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.9149. Min Act: -0.0000

Data Index: 1470106 (Python Code)

Max Activating Token Index: 524

Text #9

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.9033. Min Act: -0.0000

Data Index: 1593981 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1541126 (Python Code)

Max Activating Token Index: 427

Text #11

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.8182. Min Act: -0.0000

Data Index: 1523140 (Python Code)

Max Activating Token Index: 949

Text #12

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.6903. Min Act: -0.0000

Data Index: 1409882 (Python Code)

Max Activating Token Index: 865

Text #13

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.4273. Min Act: -0.0000

Data Index: 1411912 (Python Code)

Max Activating Token Index: 757

Text #14

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1522827 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1492109 (Python Code)

Max Activating Token Index: 405

Text #16

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.5456. Min Act: -0.0000

Data Index: 1589945 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.5449. Min Act: -0.0000

Data Index: 1379280 (Python Code)

Max Activating Token Index: 770

Text #18

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.4622. Min Act: -0.0000

Data Index: 780373 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 3.4814. Min Range: -3.4814

Max Act: 1.3354. Min Act: -0.0000

Data Index: 419509 (C4 (Web Text))

Max Activating Token Index: 68