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

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

Neuron 2746 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.8939. Min Act: -0.0001

Data Index: 1465569 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.9577. Min Act: -0.0001

Data Index: 1512075 (Python Code)

Max Activating Token Index: 643

Text #2

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.7102. Min Act: -0.0001

Data Index: 1461179 (Python Code)

Max Activating Token Index: 532

Text #3

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.5924. Min Act: -0.0001

Data Index: 1598862 (Python Code)

Max Activating Token Index: 270

Text #4

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.5720. Min Act: -0.0001

Data Index: 1482080 (Python Code)

Max Activating Token Index: 759

Text #5

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1636791 (Python Code)

Max Activating Token Index: 338

Text #6

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4880. Min Act: -0.0001

Data Index: 1594783 (Python Code)

Max Activating Token Index: 603

Text #7

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4348. Min Act: -0.0001

Data Index: 1571637 (Python Code)

Max Activating Token Index: 322

Text #8

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3166. Min Act: -0.0000

Data Index: 1456378 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4524. Min Act: -0.0001

Data Index: 1506131 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1363305 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4195. Min Act: -0.0000

Data Index: 1472221 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3565. Min Act: -0.0001

Data Index: 1416826 (Python Code)

Max Activating Token Index: 464

Text #13

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.1408. Min Act: -0.0001

Data Index: 1384971 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.1896. Min Act: -0.0001

Data Index: 1422887 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.2215. Min Act: -0.0001

Data Index: 1562059 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.4032. Min Act: -0.0001

Data Index: 1359855 (Python Code)

Max Activating Token Index: 284

Text #17

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3585. Min Act: -0.0001

Data Index: 1578601 (Python Code)

Max Activating Token Index: 374

Text #18

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1418750 (Python Code)

Max Activating Token Index: 396

Text #19

Max Range: 1.9577. Min Range: -1.9577

Max Act: 1.2269. Min Act: -0.0001

Data Index: 1407727 (Python Code)

Max Activating Token Index: 648