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

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

Neuron 556 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2801. Min Range: -2.2801

Max Act: 2.2801. Min Act: -0.0000

Data Index: 377296 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.2801. Min Range: -2.2801

Max Act: 2.0713. Min Act: -0.0000

Data Index: 215358 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 2.2801. Min Range: -2.2801

Max Act: 2.0692. Min Act: -0.0000

Data Index: 517803 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 2.2801. Min Range: -2.2801

Max Act: 2.2012. Min Act: -0.0000

Data Index: 272253 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.7944. Min Act: -0.0000

Data Index: 404209 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.7790. Min Act: -0.0000

Data Index: 1054363 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.7614. Min Act: -0.0000

Data Index: 272266 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.6607. Min Act: -0.0000

Data Index: 761339 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.7852. Min Act: -0.0000

Data Index: 129665 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.5964. Min Act: -0.0000

Data Index: 1149484 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.5893. Min Act: -0.0000

Data Index: 563471 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.4947. Min Act: -0.0000

Data Index: 725777 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.4989. Min Act: -0.0000

Data Index: 308360 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.6465. Min Act: -0.0000

Data Index: 1190890 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.7676. Min Act: -0.0000

Data Index: 1317793 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.3019. Min Act: -0.0000

Data Index: 395366 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.3883. Min Act: -0.0000

Data Index: 96460 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.4450. Min Act: -0.0000

Data Index: 391487 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.3558. Min Act: -0.0000

Data Index: 28404 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 2.2801. Min Range: -2.2801

Max Act: 1.4388. Min Act: -0.0000

Data Index: 646508 (C4 (Web Text))

Max Activating Token Index: 66