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

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

Neuron 2233 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1385529 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1934. Min Act: -0.0000

Data Index: 1574780 (Python Code)

Max Activating Token Index: 214

Text #2

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1141577 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1409510 (Python Code)

Max Activating Token Index: 861

Text #4

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1373. Min Act: -0.0000

Data Index: 348947 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1393628 (Python Code)

Max Activating Token Index: 209

Text #6

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1449832 (Python Code)

Max Activating Token Index: 160

Text #7

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1450167 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1434315 (Python Code)

Max Activating Token Index: 585

Text #9

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1393813 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1353. Min Act: -0.0000

Data Index: 521064 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1394703 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1518762 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1402228 (Python Code)

Max Activating Token Index: 928

Text #14

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1372. Min Act: -0.0000

Data Index: 61128 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1440566 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1550542 (Python Code)

Max Activating Token Index: 651

Text #17

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1402823 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1470. Min Act: -0.0000

Data Index: 677014 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1239. Min Act: -0.0000

Data Index: 722588 (C4 (Web Text))

Max Activating Token Index: 254