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

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

Neuron 754 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: 1.1209. Min Range: -1.1209

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1017771 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1240466 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9908. Min Act: -0.0000

Data Index: 154041 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.0647. Min Act: -0.0000

Data Index: 798789 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9844. Min Act: -0.0000

Data Index: 463208 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1359743 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1331095 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9428. Min Act: -0.0000

Data Index: 832526 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8969. Min Act: -0.0000

Data Index: 120199 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8719. Min Act: -0.0001

Data Index: 678303 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8926. Min Act: -0.0000

Data Index: 348909 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8949. Min Act: -0.0000

Data Index: 209321 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8398. Min Act: -0.0000

Data Index: 924425 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8407. Min Act: -0.0000

Data Index: 889904 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8885. Min Act: -0.0001

Data Index: 1087189 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1198374 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1211578 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.7756. Min Act: -0.0000

Data Index: 190123 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8655. Min Act: -0.0000

Data Index: 349058 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1072470 (C4 (Web Text))

Max Activating Token Index: 219