Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 410 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0584. Min Act: -0.0001

Data Index: 1575183 (Python Code)

Max Activating Token Index: 67

Text #1

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0828. Min Act: -0.0001

Data Index: 1495713 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0440. Min Act: -0.0001

Data Index: 1376082 (Python Code)

Max Activating Token Index: 488

Text #3

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0518. Min Act: -0.0001

Data Index: 1467516 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0456. Min Act: -0.0001

Data Index: 1598978 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0375. Min Act: -0.0001

Data Index: 1426876 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9985. Min Act: -0.0001

Data Index: 1518630 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0425. Min Act: -0.0001

Data Index: 1429996 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1473410 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9578. Min Act: -0.0001

Data Index: 1402886 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9572. Min Act: -0.0001

Data Index: 1369757 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1561876 (Python Code)

Max Activating Token Index: 229

Text #12

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9612. Min Act: -0.0001

Data Index: 1586368 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9479. Min Act: -0.0001

Data Index: 1501534 (Python Code)

Max Activating Token Index: 446

Text #14

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9228. Min Act: -0.0001

Data Index: 1556137 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8806. Min Act: -0.0001

Data Index: 1365873 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 1.0828. Min Range: -1.0828

Max Act: 1.0064. Min Act: -0.0001

Data Index: 1600453 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9034. Min Act: -0.0001

Data Index: 1498031 (Python Code)

Max Activating Token Index: 47

Text #18

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.9245. Min Act: -0.0001

Data Index: 1591022 (Python Code)

Max Activating Token Index: 368

Text #19

Max Range: 1.0828. Min Range: -1.0828

Max Act: 0.8996. Min Act: -0.0001

Data Index: 1642235 (Python Code)

Max Activating Token Index: 96