Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1520 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.6912. Min Act: -0.0000

Data Index: 465242 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1167405 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5348. Min Act: -0.0000

Data Index: 81450 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.5240. Min Act: -0.0000

Data Index: 653231 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4707. Min Act: -0.0000

Data Index: 127584 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1182882 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4724. Min Act: -0.0000

Data Index: 789274 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4406. Min Act: -0.0000

Data Index: 312788 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4412. Min Act: -0.0000

Data Index: 739733 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4581. Min Act: -0.0000

Data Index: 550499 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4638. Min Act: -0.0000

Data Index: 791128 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4569. Min Act: -0.0001

Data Index: 232752 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4436. Min Act: -0.0000

Data Index: 854623 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4567. Min Act: -0.0000

Data Index: 386307 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4240. Min Act: -0.0000

Data Index: 16757 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1065983 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1318947 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4276. Min Act: -0.0000

Data Index: 148049 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.3976. Min Act: -0.0000

Data Index: 15152 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.6912. Min Range: -0.6912

Max Act: 0.4269. Min Act: -0.0000

Data Index: 717122 (C4 (Web Text))

Max Activating Token Index: 846