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

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

Neuron 5448 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: 1.2895. Min Range: -1.2895

Max Act: 1.2895. Min Act: -0.0001

Data Index: 1326974 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.2647. Min Act: -0.0001

Data Index: 435477 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.2143. Min Act: -0.0001

Data Index: 498175 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1928. Min Act: -0.0001

Data Index: 644241 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.2196. Min Act: -0.0001

Data Index: 1163371 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1520. Min Act: -0.0001

Data Index: 318657 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1568. Min Act: -0.0001

Data Index: 1096229 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1686. Min Act: -0.0001

Data Index: 186019 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1612. Min Act: -0.0001

Data Index: 374564 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1255. Min Act: -0.0001

Data Index: 48306 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1234. Min Act: -0.0001

Data Index: 1102840 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1715. Min Act: -0.0001

Data Index: 608016 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1327. Min Act: -0.0001

Data Index: 886384 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1374. Min Act: -0.0001

Data Index: 369885 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.1115. Min Act: -0.0001

Data Index: 898839 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.0329. Min Act: -0.0001

Data Index: 80911 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.0639. Min Act: -0.0001

Data Index: 1318604 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.0699. Min Act: -0.0001

Data Index: 1352204 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.0184. Min Act: -0.0001

Data Index: 1346234 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.2895. Min Range: -1.2895

Max Act: 1.0506. Min Act: -0.0001

Data Index: 1067075 (C4 (Web Text))

Max Activating Token Index: 1020