Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2448 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0346. Min Act: -0.0001

Data Index: 753968 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0298. Min Act: -0.0001

Data Index: 531770 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0300. Min Act: -0.0000

Data Index: 630955 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0286. Min Act: -0.0001

Data Index: 799152 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0304. Min Act: -0.0000

Data Index: 385328 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0302. Min Act: -0.0001

Data Index: 873676 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0292. Min Act: -0.0001

Data Index: 371869 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1341244 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0286. Min Act: -0.0001

Data Index: 517245 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0286. Min Act: -0.0001

Data Index: 631906 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0273. Min Act: -0.0001

Data Index: 277411 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0274. Min Act: -0.0000

Data Index: 775542 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0289. Min Act: -0.0000

Data Index: 1571748 (Python Code)

Max Activating Token Index: 256

Text #13

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1002884 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0250. Min Act: -0.0001

Data Index: 94344 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0267. Min Act: -0.0000

Data Index: 598263 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0276. Min Act: -0.0000

Data Index: 1526311 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0263. Min Act: -0.0001

Data Index: 636177 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1225945 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0258. Min Act: -0.0000

Data Index: 1538047 (Python Code)

Max Activating Token Index: 949