Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 722 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0001

Data Index: 20368 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0350. Min Act: -0.0001

Data Index: 32888 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1632879 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1095664 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0320. Min Act: -0.0001

Data Index: 393109 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1636636 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1646710 (Python Code)

Max Activating Token Index: 861

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1561325 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1640782 (Python Code)

Max Activating Token Index: 494

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1501109 (Python Code)

Max Activating Token Index: 599

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0288. Min Act: -0.0001

Data Index: 860510 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1536849 (Python Code)

Max Activating Token Index: 562

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1540642 (Python Code)

Max Activating Token Index: 627

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1633062 (Python Code)

Max Activating Token Index: 599

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1475873 (Python Code)

Max Activating Token Index: 991

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1623979 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1608480 (Python Code)

Max Activating Token Index: 904

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1372950 (Python Code)

Max Activating Token Index: 624

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1194004 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1451334 (Python Code)

Max Activating Token Index: 519