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

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

Neuron 911 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1985. Min Range: -5.1985

Max Act: 5.1421. Min Act: -0.0001

Data Index: 1485494 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 5.1985. Min Range: -5.1985

Max Act: 5.1304. Min Act: -0.0001

Data Index: 1409293 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 5.1985. Min Range: -5.1985

Max Act: 5.1985. Min Act: -0.0000

Data Index: 1463625 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.8065. Min Act: -0.0001

Data Index: 1362664 (Python Code)

Max Activating Token Index: 222

Text #4

Max Range: 5.1985. Min Range: -5.1985

Max Act: 5.0948. Min Act: -0.0001

Data Index: 1396907 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 5.1985. Min Range: -5.1985

Max Act: 5.1566. Min Act: -0.0001

Data Index: 1517867 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.9564. Min Act: -0.0001

Data Index: 1415146 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.9267. Min Act: -0.0001

Data Index: 1367379 (Python Code)

Max Activating Token Index: 506

Text #8

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.9180. Min Act: -0.0001

Data Index: 1468697 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.8081. Min Act: -0.0001

Data Index: 1376913 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.7658. Min Act: -0.0001

Data Index: 1528629 (Python Code)

Max Activating Token Index: 118

Text #11

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.8497. Min Act: -0.0001

Data Index: 1604810 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.9162. Min Act: -0.0001

Data Index: 1525244 (Python Code)

Max Activating Token Index: 252

Text #13

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.9163. Min Act: -0.0001

Data Index: 1646516 (Python Code)

Max Activating Token Index: 196

Text #14

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.5726. Min Act: -0.0001

Data Index: 1454102 (Python Code)

Max Activating Token Index: 423

Text #15

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.8905. Min Act: -0.0000

Data Index: 1624726 (Python Code)

Max Activating Token Index: 238

Text #16

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.9811. Min Act: -0.0001

Data Index: 1462750 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.9721. Min Act: -0.0001

Data Index: 1622795 (Python Code)

Max Activating Token Index: 126

Text #18

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.9081. Min Act: -0.0001

Data Index: 1373144 (Python Code)

Max Activating Token Index: 177

Text #19

Max Range: 5.1985. Min Range: -5.1985

Max Act: 4.8624. Min Act: -0.0001

Data Index: 1620284 (Python Code)

Max Activating Token Index: 91