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

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

Neuron 1451 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.9102. Min Act: -0.0000

Data Index: 1544723 (Python Code)

Max Activating Token Index: 611

Text #1

Max Range: 6.0314. Min Range: -6.0314

Max Act: 6.0314. Min Act: -0.0000

Data Index: 1491445 (Python Code)

Max Activating Token Index: 504

Text #2

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.5991. Min Act: -0.0000

Data Index: 1417764 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.6452. Min Act: -0.0000

Data Index: 1583864 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.5383. Min Act: -0.0000

Data Index: 1591314 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.6483. Min Act: -0.0000

Data Index: 1610671 (Python Code)

Max Activating Token Index: 214

Text #6

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.4742. Min Act: -0.0000

Data Index: 1656135 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.4782. Min Act: -0.0000

Data Index: 1565103 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.2725. Min Act: -0.0000

Data Index: 1474918 (Python Code)

Max Activating Token Index: 443

Text #9

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.2588. Min Act: -0.0000

Data Index: 1414677 (Python Code)

Max Activating Token Index: 543

Text #10

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.0590. Min Act: -0.0000

Data Index: 1539732 (Python Code)

Max Activating Token Index: 674

Text #11

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.3957. Min Act: -0.0000

Data Index: 1389118 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.4044. Min Act: -0.0000

Data Index: 1645679 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.3412. Min Act: -0.0000

Data Index: 1590801 (Python Code)

Max Activating Token Index: 687

Text #14

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.3448. Min Act: -0.0000

Data Index: 1656887 (Python Code)

Max Activating Token Index: 890

Text #15

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.3662. Min Act: -0.0000

Data Index: 1436379 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.3375. Min Act: -0.0000

Data Index: 1535915 (Python Code)

Max Activating Token Index: 1008

Text #17

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.3242. Min Act: -0.0000

Data Index: 1376902 (Python Code)

Max Activating Token Index: 660

Text #18

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.3145. Min Act: -0.0000

Data Index: 1551703 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 6.0314. Min Range: -6.0314

Max Act: 5.2687. Min Act: -0.0000

Data Index: 1494644 (Python Code)

Max Activating Token Index: 454