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

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

Neuron 5247 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1490136 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1580931 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1414474 (Python Code)

Max Activating Token Index: 555

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1510882 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1455337 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1495125 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1409895 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1575442 (Python Code)

Max Activating Token Index: 289

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1482320 (Python Code)

Max Activating Token Index: 1013

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1617642 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1448969 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1566800 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1504462 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1053550 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1393156 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0258. Min Act: -0.0002

Data Index: 464694 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1159321 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1601992 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0239. Min Act: -0.0002

Data Index: 225733 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1496100 (Python Code)

Max Activating Token Index: 118