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

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

Neuron 1526 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1564956 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1377. Min Act: -0.0000

Data Index: 682054 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1052905 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1284. Min Act: -0.0000

Data Index: 22135 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1276. Min Act: -0.0000

Data Index: 80357 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1197. Min Act: -0.0000

Data Index: 823439 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1232. Min Act: -0.0001

Data Index: 97301 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1506092 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1132. Min Act: -0.0000

Data Index: 404577 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1243244 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1385346 (Python Code)

Max Activating Token Index: 772

Text #11

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1023. Min Act: -0.0000

Data Index: 556765 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1276052 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1018672 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1218391 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0954. Min Act: -0.0001

Data Index: 262986 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1390969 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1553027 (Python Code)

Max Activating Token Index: 774

Text #18

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1038. Min Act: -0.0001

Data Index: 881641 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1077. Min Act: -0.0000

Data Index: 513479 (C4 (Web Text))

Max Activating Token Index: 1003