Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1949 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1022. Min Act: -0.0001

Data Index: 1550169 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1569. Min Act: -0.0001

Data Index: 1563854 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1010. Min Act: -0.0001

Data Index: 1635768 (Python Code)

Max Activating Token Index: 995

Text #3

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1189. Min Act: -0.0001

Data Index: 1502831 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0342. Min Act: -0.0001

Data Index: 1390867 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0989. Min Act: -0.0001

Data Index: 1409450 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0916. Min Act: -0.0001

Data Index: 1513471 (Python Code)

Max Activating Token Index: 627

Text #7

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0934. Min Act: -0.0001

Data Index: 1599661 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0993. Min Act: -0.0001

Data Index: 1397175 (Python Code)

Max Activating Token Index: 701

Text #9

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1227. Min Act: -0.0001

Data Index: 1575271 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1188. Min Act: -0.0001

Data Index: 1441176 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0375. Min Act: -0.0001

Data Index: 1636104 (Python Code)

Max Activating Token Index: 532

Text #12

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0628. Min Act: -0.0001

Data Index: 1485422 (Python Code)

Max Activating Token Index: 826

Text #13

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0212. Min Act: -0.0001

Data Index: 1603901 (Python Code)

Max Activating Token Index: 160

Text #14

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0786. Min Act: -0.0001

Data Index: 1423226 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9813. Min Act: -0.0001

Data Index: 1626765 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0191. Min Act: -0.0001

Data Index: 1381920 (Python Code)

Max Activating Token Index: 134

Text #17

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1632475 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0121. Min Act: -0.0001

Data Index: 1484012 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0412. Min Act: -0.0001

Data Index: 1446677 (Python Code)

Max Activating Token Index: 17