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

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

Neuron 4435 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.8149. Min Act: -0.0000

Data Index: 103569 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.9974. Min Act: -0.0000

Data Index: 205962 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.4468. Min Act: -0.0001

Data Index: 1031398 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.5256. Min Act: -0.0000

Data Index: 725261 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.4813. Min Act: -0.0000

Data Index: 370050 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.3341. Min Act: -0.0000

Data Index: 1033473 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.3424. Min Act: -0.0000

Data Index: 1183470 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.0903. Min Act: -0.0000

Data Index: 373022 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.0505. Min Act: -0.0000

Data Index: 1338671 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.0215. Min Act: -0.0000

Data Index: 1063011 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.9526. Min Act: -0.0001

Data Index: 1064178 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.1649. Min Act: -0.0000

Data Index: 91404 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.1323. Min Act: -0.0000

Data Index: 525779 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.1811. Min Act: -0.0000

Data Index: 471825 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8859. Min Act: -0.0000

Data Index: 760858 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8273. Min Act: -0.0001

Data Index: 1272960 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 2.9974. Min Range: -2.9974

Max Act: 2.0240. Min Act: -0.0000

Data Index: 1019322 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8916. Min Act: -0.0001

Data Index: 1057857 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.7875. Min Act: -0.0001

Data Index: 845769 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 2.9974. Min Range: -2.9974

Max Act: 1.8907. Min Act: -0.0000

Data Index: 945246 (C4 (Web Text))

Max Activating Token Index: 418