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

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

Neuron 4689 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4988. Min Range: -2.4988

Max Act: 2.4988. Min Act: -0.0000

Data Index: 1480844 (Python Code)

Max Activating Token Index: 400

Text #1

Max Range: 2.4988. Min Range: -2.4988

Max Act: 2.2889. Min Act: -0.0000

Data Index: 1365606 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 2.4988. Min Range: -2.4988

Max Act: 2.1517. Min Act: -0.0000

Data Index: 1567091 (Python Code)

Max Activating Token Index: 71

Text #3

Max Range: 2.4988. Min Range: -2.4988

Max Act: 2.0481. Min Act: -0.0000

Data Index: 1385625 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.9896. Min Act: -0.0000

Data Index: 1365030 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.9425. Min Act: -0.0000

Data Index: 1549477 (Python Code)

Max Activating Token Index: 278

Text #6

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.9538. Min Act: -0.0000

Data Index: 1535932 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 2.4988. Min Range: -2.4988

Max Act: 2.0175. Min Act: -0.0000

Data Index: 1440963 (Python Code)

Max Activating Token Index: 664

Text #8

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.8734. Min Act: -0.0000

Data Index: 1534588 (Python Code)

Max Activating Token Index: 616

Text #9

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1477128 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.6022. Min Act: -0.0000

Data Index: 1469427 (Python Code)

Max Activating Token Index: 131

Text #11

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.6406. Min Act: -0.0000

Data Index: 1544157 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1526379 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.6228. Min Act: -0.0000

Data Index: 1514145 (Python Code)

Max Activating Token Index: 812

Text #14

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1630131 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.5158. Min Act: -0.0000

Data Index: 1524033 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1406792 (Python Code)

Max Activating Token Index: 887

Text #17

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.4846. Min Act: -0.0000

Data Index: 1499933 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1360682 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 2.4988. Min Range: -2.4988

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1520868 (Python Code)

Max Activating Token Index: 912