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

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

Neuron 711 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1533. Min Range: -2.1533

Max Act: 2.1533. Min Act: -0.0000

Data Index: 376418 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 2.1533. Min Range: -2.1533

Max Act: 2.1156. Min Act: -0.0000

Data Index: 370422 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.8539. Min Act: -0.0000

Data Index: 1054447 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.8090. Min Act: -0.0000

Data Index: 502348 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1532882 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1529833 (Python Code)

Max Activating Token Index: 1006

Text #6

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1551016 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.0906. Min Act: -0.0000

Data Index: 1603664 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1604593 (Python Code)

Max Activating Token Index: 579

Text #9

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.1447. Min Act: -0.0000

Data Index: 332335 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 2.1533. Min Range: -2.1533

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1427445 (Python Code)

Max Activating Token Index: 952

Text #11

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1417804 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1367628 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1618100 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1583864 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 2.1533. Min Range: -2.1533

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1382824 (Python Code)

Max Activating Token Index: 188

Text #16

Max Range: 2.1533. Min Range: -2.1533

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1495167 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1548594 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 2.1533. Min Range: -2.1533

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1419724 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 2.1533. Min Range: -2.1533

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1413153 (Python Code)

Max Activating Token Index: 322