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

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

Neuron 3976 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: 0.7088. Min Range: -0.7088

Max Act: 0.6961. Min Act: -0.0000

Data Index: 995309 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.7088. Min Act: -0.0000

Data Index: 4512 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1150270 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1325700 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4771. Min Act: -0.0000

Data Index: 583653 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4727. Min Act: -0.0000

Data Index: 804380 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4492. Min Act: -0.0000

Data Index: 856896 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4153. Min Act: -0.0000

Data Index: 61777 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4376. Min Act: -0.0000

Data Index: 347857 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4374. Min Act: -0.0000

Data Index: 792437 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1039940 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4049. Min Act: -0.0000

Data Index: 922694 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.3949. Min Act: -0.0000

Data Index: 805966 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1283168 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1408614 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.3844. Min Act: -0.0000

Data Index: 115683 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.3686. Min Act: -0.0000

Data Index: 237522 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.3475. Min Act: -0.0000

Data Index: 390869 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.4029. Min Act: -0.0000

Data Index: 269116 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.7088. Min Range: -0.7088

Max Act: 0.3430. Min Act: -0.0000

Data Index: 75115 (C4 (Web Text))

Max Activating Token Index: 828