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

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

Neuron 6000 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3755. Min Act: -0.0000

Data Index: 642366 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3718. Min Act: -0.0000

Data Index: 628687 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3646. Min Act: -0.0000

Data Index: 967583 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3074. Min Act: -0.0000

Data Index: 687246 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3127. Min Act: -0.0000

Data Index: 969133 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2935. Min Act: -0.0000

Data Index: 456618 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2992. Min Act: -0.0000

Data Index: 726379 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2936. Min Act: -0.0000

Data Index: 459012 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2755. Min Act: -0.0000

Data Index: 838822 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1175102 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1037283 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2738. Min Act: -0.0000

Data Index: 55284 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2716. Min Act: -0.0000

Data Index: 605785 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2617. Min Act: -0.0000

Data Index: 7487 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2805. Min Act: -0.0000

Data Index: 951916 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1073987 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2692. Min Act: -0.0000

Data Index: 614749 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2778. Min Act: -0.0000

Data Index: 841249 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2883. Min Act: -0.0000

Data Index: 704043 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2780. Min Act: -0.0000

Data Index: 930757 (C4 (Web Text))

Max Activating Token Index: 850