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

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

Neuron 2665 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0389. Min Act: -0.0001

Data Index: 495554 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0327. Min Act: -0.0001

Data Index: 161421 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1027828 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1503195 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1188461 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1302835 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1341442 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0248. Min Act: -0.0001

Data Index: 629834 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1129427 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1554988 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0293. Min Act: -0.0001

Data Index: 946061 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0276. Min Act: -0.0001

Data Index: 447586 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1446414 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0283. Min Act: -0.0001

Data Index: 137072 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0258. Min Act: -0.0001

Data Index: 410169 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1369406 (Python Code)

Max Activating Token Index: 622

Text #16

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1605656 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1654763 (Python Code)

Max Activating Token Index: 456

Text #18

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0249. Min Act: -0.0001

Data Index: 327530 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0389. Min Range: -0.0389

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1516810 (Python Code)

Max Activating Token Index: 772