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

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

Neuron 1796 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: 1.3225. Min Range: -1.3225

Max Act: 1.3225. Min Act: -0.0001

Data Index: 1532621 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1622838 (Python Code)

Max Activating Token Index: 481

Text #2

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1509963 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1617330 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1607165 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1639020 (Python Code)

Max Activating Token Index: 481

Text #6

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1384686 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1469992 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9693. Min Act: -0.0001

Data Index: 1606955 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1496545 (Python Code)

Max Activating Token Index: 321

Text #10

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9410. Min Act: -0.0001

Data Index: 1570345 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1638435 (Python Code)

Max Activating Token Index: 600

Text #12

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.8998. Min Act: -0.0001

Data Index: 1600573 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1544980 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 1.3225. Min Range: -1.3225

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1530766 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1537943 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9517. Min Act: -0.0001

Data Index: 267692 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1566114 (Python Code)

Max Activating Token Index: 622

Text #18

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1497145 (Python Code)

Max Activating Token Index: 141

Text #19

Max Range: 1.3225. Min Range: -1.3225

Max Act: 0.8327. Min Act: -0.0001

Data Index: 1597903 (Python Code)

Max Activating Token Index: 752