Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2703 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1544791 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1503113 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1494313 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1602937 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1603562 (Python Code)

Max Activating Token Index: 346

Text #5

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1381415 (Python Code)

Max Activating Token Index: 270

Text #6

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1643230 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1401966 (Python Code)

Max Activating Token Index: 950

Text #8

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1419977 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1540482 (Python Code)

Max Activating Token Index: 332

Text #10

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1462175 (Python Code)

Max Activating Token Index: 585

Text #11

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1483372 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1626997 (Python Code)

Max Activating Token Index: 796

Text #13

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1481130 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1596306 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1598728 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1620305 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1567133 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1482729 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1476110 (Python Code)

Max Activating Token Index: 675