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

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

Neuron 3003 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4782. Min Act: -0.0002

Data Index: 1426451 (Python Code)

Max Activating Token Index: 211

Text #1

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4528. Min Act: -0.0002

Data Index: 1509679 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4773. Min Act: -0.0002

Data Index: 1546804 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4539. Min Act: -0.0002

Data Index: 1399905 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4584. Min Act: -0.0002

Data Index: 1624777 (Python Code)

Max Activating Token Index: 242

Text #5

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4507. Min Act: -0.0002

Data Index: 1615544 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4272. Min Act: -0.0002

Data Index: 1465832 (Python Code)

Max Activating Token Index: 628

Text #7

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4292. Min Act: -0.0002

Data Index: 1401456 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4186. Min Act: -0.0002

Data Index: 1453681 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4232. Min Act: -0.0002

Data Index: 1602213 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4122. Min Act: -0.0002

Data Index: 1392068 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3928. Min Act: -0.0002

Data Index: 1429373 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3904. Min Act: -0.0002

Data Index: 1418030 (Python Code)

Max Activating Token Index: 555

Text #13

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3752. Min Act: -0.0002

Data Index: 1531171 (Python Code)

Max Activating Token Index: 962

Text #14

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3960. Min Act: -0.0002

Data Index: 1554081 (Python Code)

Max Activating Token Index: 485

Text #15

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3935. Min Act: -0.0002

Data Index: 1446321 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.4160. Min Act: -0.0002

Data Index: 1475959 (Python Code)

Max Activating Token Index: 841

Text #17

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3879. Min Act: -0.0002

Data Index: 1421629 (Python Code)

Max Activating Token Index: 475

Text #18

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3761. Min Act: -0.0002

Data Index: 1377077 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 0.4782. Min Range: -0.4782

Max Act: 0.3821. Min Act: -0.0002

Data Index: 1561125 (Python Code)

Max Activating Token Index: 550