Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4822 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.8578. Min Act: -0.0000

Data Index: 1403206 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7973. Min Act: -0.0000

Data Index: 1470307 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.4081. Min Act: -0.0000

Data Index: 916398 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6504. Min Act: -0.0000

Data Index: 1240017 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1044708 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7570. Min Act: -0.0000

Data Index: 1521842 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.4739. Min Act: -0.0000

Data Index: 965489 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.5448. Min Act: -0.0000

Data Index: 1030693 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6436. Min Act: -0.0000

Data Index: 65176 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.6683. Min Act: -0.0000

Data Index: 1519435 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.5094. Min Act: -0.0000

Data Index: 286996 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.7164. Min Act: -0.0000

Data Index: 1605218 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1626747 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.4579. Min Act: -0.0000

Data Index: 159666 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.3802. Min Act: -0.0000

Data Index: 1290040 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.3377. Min Act: -0.0000

Data Index: 686277 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.4659. Min Act: -0.0000

Data Index: 488246 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.3928. Min Act: -0.0000

Data Index: 1637074 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1374424 (Python Code)

Max Activating Token Index: 717

Text #19

Max Range: 1.8578. Min Range: -1.8578

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1448115 (Python Code)

Max Activating Token Index: 174