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

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

Neuron 3286 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.8063. Min Act: -0.0000

Data Index: 618806 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 3.0739. Min Range: -3.0739

Max Act: 3.0496. Min Act: -0.0000

Data Index: 897644 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.6630. Min Act: -0.0000

Data Index: 101378 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.6534. Min Act: -0.0000

Data Index: 581496 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.0739. Min Range: -3.0739

Max Act: 3.0739. Min Act: -0.0000

Data Index: 973286 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.7436. Min Act: -0.0000

Data Index: 871211 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.4153. Min Act: -0.0000

Data Index: 386050 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.7449. Min Act: -0.0000

Data Index: 1063617 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.3918. Min Act: -0.0000

Data Index: 1073613 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.4525. Min Act: -0.0000

Data Index: 1193827 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.4089. Min Act: -0.0000

Data Index: 343839 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.1133. Min Act: -0.0000

Data Index: 405911 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.4592. Min Act: -0.0000

Data Index: 806657 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.2022. Min Act: -0.0000

Data Index: 651011 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 3.0739. Min Range: -3.0739

Max Act: 1.9739. Min Act: -0.0000

Data Index: 779766 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.2848. Min Act: -0.0000

Data Index: 953482 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.1328. Min Act: -0.0000

Data Index: 214742 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.1121. Min Act: -0.0000

Data Index: 1139507 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 3.0739. Min Range: -3.0739

Max Act: 1.9895. Min Act: -0.0000

Data Index: 967059 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 3.0739. Min Range: -3.0739

Max Act: 2.1792. Min Act: -0.0000

Data Index: 1137847 (C4 (Web Text))

Max Activating Token Index: 53