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

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

Neuron 4166 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1108748 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3849. Min Act: -0.0000

Data Index: 935025 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3574. Min Act: -0.0000

Data Index: 707850 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3090. Min Act: -0.0000

Data Index: 49613 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3251. Min Act: -0.0000

Data Index: 990281 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3100. Min Act: -0.0000

Data Index: 831525 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2971. Min Act: -0.0000

Data Index: 393127 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3092. Min Act: -0.0000

Data Index: 535029 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1228962 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1104810 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2901. Min Act: -0.0000

Data Index: 460223 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2961. Min Act: -0.0000

Data Index: 122787 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1342469 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2789. Min Act: -0.0000

Data Index: 882188 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2606. Min Act: -0.0000

Data Index: 681844 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2842. Min Act: -0.0000

Data Index: 455258 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2644. Min Act: -0.0000

Data Index: 782005 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2759. Min Act: -0.0000

Data Index: 546437 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2940. Min Act: 0.0000

Data Index: 1350494 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2656. Min Act: -0.0000

Data Index: 904853 (C4 (Web Text))

Max Activating Token Index: 632