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

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

Neuron 5562 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: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1516830 (Python Code)

Max Activating Token Index: 641

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1553362 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1493096 (Python Code)

Max Activating Token Index: 679

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1472203 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1612208 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1381274 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0303. Min Act: -0.0002

Data Index: 562932 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0282. Min Act: -0.0002

Data Index: 143270 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1640116 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1451763 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0282. Min Act: -0.0002

Data Index: 756051 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0265. Min Act: -0.0002

Data Index: 230506 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1504716 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1506703 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1464082 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1522229 (Python Code)

Max Activating Token Index: 355

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1464339 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1595156 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1560417 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0259. Min Act: -0.0002

Data Index: 351913 (C4 (Web Text))

Max Activating Token Index: 546