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

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

Neuron 778 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1483937 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1370152 (Python Code)

Max Activating Token Index: 937

Text #2

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0267. Min Act: -0.0001

Data Index: 293635 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1604683 (Python Code)

Max Activating Token Index: 936

Text #4

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1487243 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0278. Min Act: -0.0001

Data Index: 563490 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1559394 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0244. Min Act: -0.0001

Data Index: 933958 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0237. Min Act: -0.0001

Data Index: 452152 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0265. Min Act: -0.0001

Data Index: 121503 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0224. Min Act: -0.0001

Data Index: 572115 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1599468 (Python Code)

Max Activating Token Index: 794

Text #12

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1398272 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0271. Min Act: -0.0001

Data Index: 775743 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0230. Min Act: -0.0001

Data Index: 597915 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1069443 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0232. Min Act: -0.0001

Data Index: 960827 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0245. Min Act: -0.0001

Data Index: 323654 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1481980 (Python Code)

Max Activating Token Index: 1008

Text #19

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1200146 (C4 (Web Text))

Max Activating Token Index: 207