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

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

Neuron 3593 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.4647. Min Act: -0.0000

Data Index: 1531804 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.6275. Min Act: -0.0000

Data Index: 1458216 (Python Code)

Max Activating Token Index: 1022

Text #2

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.3387. Min Act: -0.0000

Data Index: 1576349 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.2136. Min Act: -0.0000

Data Index: 1405226 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.2267. Min Act: -0.0000

Data Index: 1513143 (Python Code)

Max Activating Token Index: 876

Text #5

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.1730. Min Act: -0.0000

Data Index: 1607690 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.2590. Min Act: -0.0000

Data Index: 1522138 (Python Code)

Max Activating Token Index: 657

Text #7

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.2645. Min Act: -0.0000

Data Index: 1400637 (Python Code)

Max Activating Token Index: 731

Text #8

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.4750. Min Act: -0.0000

Data Index: 1570345 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 2.6275. Min Range: -2.6275

Max Act: 1.9550. Min Act: -0.0000

Data Index: 1394331 (Python Code)

Max Activating Token Index: 678

Text #10

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.0873. Min Act: -0.0000

Data Index: 1648919 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.1429. Min Act: -0.0000

Data Index: 1534376 (Python Code)

Max Activating Token Index: 126

Text #12

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.2165. Min Act: -0.0000

Data Index: 1562152 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.1419. Min Act: -0.0000

Data Index: 1394553 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.1006. Min Act: -0.0000

Data Index: 1560693 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.0183. Min Act: -0.0000

Data Index: 1432695 (Python Code)

Max Activating Token Index: 1007

Text #16

Max Range: 2.6275. Min Range: -2.6275

Max Act: 1.9917. Min Act: -0.0000

Data Index: 1360861 (Python Code)

Max Activating Token Index: 773

Text #17

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.2295. Min Act: -0.0000

Data Index: 1454729 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 2.6275. Min Range: -2.6275

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1484136 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 2.6275. Min Range: -2.6275

Max Act: 2.1657. Min Act: -0.0000

Data Index: 1510220 (Python Code)

Max Activating Token Index: 1020