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

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

Neuron 4296 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0003

Data Index: 233488 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1199996 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0826. Min Act: -0.0002

Data Index: 729216 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0805. Min Act: -0.0002

Data Index: 696001 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0776. Min Act: -0.0002

Data Index: 733936 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0741. Min Act: -0.0002

Data Index: 773205 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0735. Min Act: -0.0002

Data Index: 366458 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0739. Min Act: -0.0002

Data Index: 978321 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1057998 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0702. Min Act: -0.0002

Data Index: 823829 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0698. Min Act: -0.0002

Data Index: 264740 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0712. Min Act: -0.0002

Data Index: 446305 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0714. Min Act: -0.0003

Data Index: 202671 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1334501 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1352833 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0688. Min Act: -0.0002

Data Index: 192152 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1087133 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0683. Min Act: -0.0002

Data Index: 286967 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0703. Min Act: -0.0002

Data Index: 960368 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1217977 (C4 (Web Text))

Max Activating Token Index: 629