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

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

Neuron 3565 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1475797 (Python Code)

Max Activating Token Index: 355

Text #1

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.8302. Min Act: 0.0000

Data Index: 1489793 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7850. Min Act: -0.0000

Data Index: 541985 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1529057 (Python Code)

Max Activating Token Index: 890

Text #4

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1563109 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1561616 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1525709 (Python Code)

Max Activating Token Index: 986

Text #7

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1548602 (Python Code)

Max Activating Token Index: 176

Text #8

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1593307 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1445891 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1418985 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7098. Min Act: 0.0000

Data Index: 1566103 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.7437. Min Act: 0.0000

Data Index: 635229 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1434292 (Python Code)

Max Activating Token Index: 301

Text #14

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1458653 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1505122 (Python Code)

Max Activating Token Index: 51

Text #16

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1491116 (Python Code)

Max Activating Token Index: 660

Text #17

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1442227 (Python Code)

Max Activating Token Index: 333

Text #18

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.6477. Min Act: 0.0001

Data Index: 1500408 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 0.8302. Min Range: -0.8302

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1488844 (Python Code)

Max Activating Token Index: 87