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

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

Neuron 4655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1382879 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1491231 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1361683 (Python Code)

Max Activating Token Index: 986

Text #3

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1653643 (Python Code)

Max Activating Token Index: 996

Text #4

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1418948 (Python Code)

Max Activating Token Index: 914

Text #5

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1520758 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1532986 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1521185 (Python Code)

Max Activating Token Index: 108

Text #8

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1453248 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1372027 (Python Code)

Max Activating Token Index: 295

Text #10

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1554843 (Python Code)

Max Activating Token Index: 716

Text #11

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1532815 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1576826 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1373628 (Python Code)

Max Activating Token Index: 729

Text #14

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1440508 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1386747 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1415166 (Python Code)

Max Activating Token Index: 1009

Text #17

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1646377 (Python Code)

Max Activating Token Index: 896

Text #18

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1475215 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1426188 (Python Code)

Max Activating Token Index: 764