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

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

Neuron 227 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0001

Data Index: 458160 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0772. Min Act: -0.0001

Data Index: 942023 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0720. Min Act: -0.0001

Data Index: 468977 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0732. Min Act: -0.0001

Data Index: 504082 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0688. Min Act: -0.0001

Data Index: 889694 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0679. Min Act: -0.0001

Data Index: 147855 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0669. Min Act: -0.0001

Data Index: 143385 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0665. Min Act: -0.0001

Data Index: 101978 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0657. Min Act: -0.0001

Data Index: 841776 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0623. Min Act: -0.0001

Data Index: 467254 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1091547 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0665. Min Act: -0.0001

Data Index: 981689 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1309821 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0679. Min Act: -0.0001

Data Index: 729065 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0707. Min Act: -0.0001

Data Index: 779806 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1303343 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0696. Min Act: -0.0001

Data Index: 862555 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0524. Min Act: -0.0001

Data Index: 342471 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0591. Min Act: -0.0001

Data Index: 606616 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0621. Min Act: -0.0001

Data Index: 393697 (C4 (Web Text))

Max Activating Token Index: 838