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

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

Neuron 4526 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.7285. Min Act: -0.0000

Data Index: 1496211 (Python Code)

Max Activating Token Index: 587

Text #1

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1625141 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1467164 (Python Code)

Max Activating Token Index: 699

Text #3

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.5065. Min Act: -0.0000

Data Index: 190590 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1459904 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1481709 (Python Code)

Max Activating Token Index: 309

Text #6

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.3229. Min Act: -0.0000

Data Index: 439456 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.3071. Min Act: -0.0000

Data Index: 424488 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.2392. Min Act: -0.0000

Data Index: 492526 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1364711 (Python Code)

Max Activating Token Index: 714

Text #10

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1417165 (Python Code)

Max Activating Token Index: 632

Text #11

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1400101 (Python Code)

Max Activating Token Index: 853

Text #12

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.2239. Min Act: -0.0000

Data Index: 855014 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1577107 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1451731 (Python Code)

Max Activating Token Index: 99

Text #15

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.2498. Min Act: -0.0000

Data Index: 666529 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1625126 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.2811. Min Act: -0.0000

Data Index: 1552570 (Python Code)

Max Activating Token Index: 299

Text #18

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1521847 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 1.7285. Min Range: -1.7285

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1595792 (Python Code)

Max Activating Token Index: 531