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

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

Neuron 1642 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0509. Min Range: -1.0509

Max Act: 1.0509. Min Act: -0.0003

Data Index: 1392585 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9448. Min Act: -0.0003

Data Index: 1459504 (Python Code)

Max Activating Token Index: 963

Text #2

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9328. Min Act: -0.0003

Data Index: 1409675 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8761. Min Act: -0.0003

Data Index: 1364847 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8644. Min Act: -0.0004

Data Index: 1582500 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9141. Min Act: -0.0003

Data Index: 1403972 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8641. Min Act: -0.0003

Data Index: 1543680 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8110. Min Act: -0.0003

Data Index: 1567064 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7901. Min Act: -0.0003

Data Index: 1597603 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7570. Min Act: -0.0003

Data Index: 1548295 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7805. Min Act: -0.0003

Data Index: 1426587 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7314. Min Act: -0.0003

Data Index: 1570598 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7001. Min Act: -0.0003

Data Index: 1388035 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7155. Min Act: -0.0003

Data Index: 1463675 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6958. Min Act: -0.0003

Data Index: 1411680 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6958. Min Act: -0.0003

Data Index: 1557317 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7383. Min Act: -0.0003

Data Index: 1653326 (Python Code)

Max Activating Token Index: 972

Text #17

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6832. Min Act: -0.0003

Data Index: 1442452 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7042. Min Act: -0.0003

Data Index: 1450904 (Python Code)

Max Activating Token Index: 566

Text #19

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6582. Min Act: -0.0003

Data Index: 1644079 (Python Code)

Max Activating Token Index: 733