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

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

Neuron 5932 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1558685 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1226321 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1381. Min Act: -0.0000

Data Index: 2422 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1426945 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1450776 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1162757 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1108. Min Act: -0.0000

Data Index: 447042 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1030219 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1095. Min Act: -0.0000

Data Index: 967427 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1178534 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1219237 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1061. Min Act: -0.0000

Data Index: 335647 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1089625 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1288979 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1056. Min Act: -0.0000

Data Index: 582008 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1053. Min Act: -0.0000

Data Index: 49708 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1045. Min Act: -0.0000

Data Index: 131263 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1424662 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1394868 (Python Code)

Max Activating Token Index: 213

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1326360 (C4 (Web Text))

Max Activating Token Index: 985