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

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

Neuron 2713 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.7412. Min Act: -0.0000

Data Index: 1482829 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.6012. Min Act: -0.0000

Data Index: 1497841 (Python Code)

Max Activating Token Index: 689

Text #2

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.3781. Min Act: -0.0000

Data Index: 1551339 (Python Code)

Max Activating Token Index: 625

Text #3

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.3832. Min Act: -0.0000

Data Index: 1584915 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.7443. Min Act: -0.0000

Data Index: 1426235 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.4802. Min Act: -0.0000

Data Index: 1398533 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.4677. Min Act: -0.0000

Data Index: 1424542 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.4542. Min Act: -0.0000

Data Index: 1419084 (Python Code)

Max Activating Token Index: 782

Text #8

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.3582. Min Act: -0.0000

Data Index: 1623631 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.6214. Min Act: -0.0000

Data Index: 1498827 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.3520. Min Act: -0.0000

Data Index: 1537566 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.5976. Min Act: -0.0000

Data Index: 1568254 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 2.7443. Min Range: -2.7443

Max Act: 2.1790. Min Act: -0.0000

Data Index: 1493415 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 2.7443. Min Range: -2.7443

Max Act: 1.7081. Min Act: -0.0001

Data Index: 54359 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 2.7443. Min Range: -2.7443

Max Act: 1.6937. Min Act: -0.0001

Data Index: 64663 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 2.7443. Min Range: -2.7443

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1508915 (Python Code)

Max Activating Token Index: 405

Text #16

Max Range: 2.7443. Min Range: -2.7443

Max Act: 1.4915. Min Act: -0.0001

Data Index: 538487 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 2.7443. Min Range: -2.7443

Max Act: 1.7013. Min Act: -0.0001

Data Index: 463131 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 2.7443. Min Range: -2.7443

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1581484 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 2.7443. Min Range: -2.7443

Max Act: 1.6177. Min Act: -0.0001

Data Index: 1272644 (C4 (Web Text))

Max Activating Token Index: 937