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

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

Neuron 775 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: 3.1903. Min Range: -3.1903

Max Act: 3.1903. Min Act: -0.0000

Data Index: 582593 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.8540. Min Act: -0.0000

Data Index: 168347 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.7080. Min Act: -0.0000

Data Index: 418746 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.5285. Min Act: -0.0000

Data Index: 872627 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3666. Min Act: -0.0000

Data Index: 570849 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3356. Min Act: -0.0000

Data Index: 843103 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.1074. Min Act: -0.0000

Data Index: 572017 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.1801. Min Act: -0.0000

Data Index: 953932 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0472. Min Act: -0.0000

Data Index: 924123 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0094. Min Act: -0.0000

Data Index: 963212 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0183. Min Act: -0.0000

Data Index: 642567 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0834. Min Act: -0.0000

Data Index: 909304 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0514. Min Act: -0.0000

Data Index: 683270 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.9313. Min Act: -0.0000

Data Index: 360328 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0115. Min Act: -0.0000

Data Index: 738130 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.9904. Min Act: -0.0000

Data Index: 58938 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.9526. Min Act: -0.0000

Data Index: 229297 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.9691. Min Act: -0.0000

Data Index: 233775 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.9530. Min Act: -0.0000

Data Index: 543758 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.9396. Min Act: -0.0000

Data Index: 175760 (C4 (Web Text))

Max Activating Token Index: 114