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

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

Neuron 4188 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: 1.8346. Min Range: -1.8346

Max Act: 1.8346. Min Act: -0.0000

Data Index: 1258904 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.6975. Min Act: -0.0000

Data Index: 919806 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.4813. Min Act: 0.0000

Data Index: 1525299 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.3391. Min Act: 0.0000

Data Index: 1489103 (Python Code)

Max Activating Token Index: 1010

Text #4

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1420854 (Python Code)

Max Activating Token Index: 386

Text #5

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.5218. Min Act: -0.0000

Data Index: 753762 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.2664. Min Act: 0.0000

Data Index: 1447884 (Python Code)

Max Activating Token Index: 682

Text #7

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.2964. Min Act: 0.0000

Data Index: 1523225 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.3220. Min Act: -0.0000

Data Index: 917106 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1500055 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.0666. Min Act: 0.0000

Data Index: 1492274 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1439213 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1372822 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1411458 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1520582 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1604227 (Python Code)

Max Activating Token Index: 771

Text #16

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1017851 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1431824 (Python Code)

Max Activating Token Index: 909

Text #18

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.1615. Min Act: -0.0000

Data Index: 190655 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 1.8346. Min Range: -1.8346

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1381896 (Python Code)

Max Activating Token Index: 545