Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3644 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.0123. Min Act: -0.0000

Data Index: 243404 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1622. Min Act: -0.0000

Data Index: 38584 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1665. Min Act: -0.0000

Data Index: 521937 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1661. Min Act: -0.0000

Data Index: 403649 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1149780 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1456. Min Act: -0.0000

Data Index: 490974 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1073341 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1157554 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1317908 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1244768 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1303835 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1331. Min Act: -0.0000

Data Index: 806751 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1370. Min Act: -0.0000

Data Index: 95129 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1360. Min Act: -0.0000

Data Index: 727917 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1351. Min Act: -0.0000

Data Index: 115972 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1278. Min Act: -0.0000

Data Index: 671873 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1318. Min Act: -0.0000

Data Index: 206697 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1252. Min Act: -0.0000

Data Index: 356342 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1309. Min Act: -0.0000

Data Index: 277904 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1210261 (C4 (Web Text))

Max Activating Token Index: 68