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

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

Neuron 4120 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9891. Min Act: -0.0000

Data Index: 738686 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.9588. Min Act: -0.0000

Data Index: 296558 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8945. Min Act: -0.0000

Data Index: 406321 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8899. Min Act: -0.0000

Data Index: 386496 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8447. Min Act: -0.0000

Data Index: 806908 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8370. Min Act: -0.0000

Data Index: 593311 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7636. Min Act: -0.0000

Data Index: 167733 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7965. Min Act: -0.0000

Data Index: 471829 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1170839 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1330049 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7650. Min Act: -0.0000

Data Index: 468951 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7741. Min Act: -0.0000

Data Index: 343564 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7687. Min Act: -0.0000

Data Index: 744062 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.8069. Min Act: -0.0000

Data Index: 468885 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7328. Min Act: -0.0000

Data Index: 26569 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1166122 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1301174 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7429. Min Act: -0.0000

Data Index: 30175 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7435. Min Act: -0.0000

Data Index: 981690 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.9891. Min Range: -0.9891

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1066712 (C4 (Web Text))

Max Activating Token Index: 125