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

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

Neuron 3283 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9648. Min Act: -0.0000

Data Index: 743262 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7637. Min Act: -0.0000

Data Index: 537073 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7000. Min Act: 0.0000

Data Index: 902645 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6153. Min Act: 0.0000

Data Index: 955796 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5561. Min Act: 0.0000

Data Index: 124166 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5446. Min Act: -0.0000

Data Index: 777724 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1183307 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5086. Min Act: -0.0000

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5096. Min Act: -0.0000

Data Index: 956880 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4779. Min Act: -0.0000

Data Index: 174024 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4890. Min Act: -0.0000

Data Index: 999609 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4265. Min Act: -0.0000

Data Index: 321448 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4456. Min Act: -0.0000

Data Index: 411686 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1090702 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1446401 (Python Code)

Max Activating Token Index: 412

Text #15

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4265. Min Act: -0.0000

Data Index: 578332 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4098. Min Act: -0.0000

Data Index: 106731 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1469448 (Python Code)

Max Activating Token Index: 480

Text #18

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4192. Min Act: -0.0000

Data Index: 948528 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.3857. Min Act: -0.0000

Data Index: 439315 (C4 (Web Text))

Max Activating Token Index: 201