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

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

Neuron 5645 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: 0.8883. Min Range: -0.8883

Max Act: 0.8134. Min Act: -0.0000

Data Index: 873496 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.8883. Min Act: -0.0001

Data Index: 196514 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1249699 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.8047. Min Act: -0.0000

Data Index: 830899 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1231956 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7551. Min Act: -0.0000

Data Index: 569660 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6441. Min Act: -0.0000

Data Index: 870912 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7424. Min Act: -0.0000

Data Index: 229644 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7626. Min Act: -0.0000

Data Index: 359968 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7557. Min Act: -0.0000

Data Index: 932847 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6684. Min Act: -0.0000

Data Index: 278621 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6794. Min Act: -0.0000

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1212734 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1307155 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1159464 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6804. Min Act: -0.0000

Data Index: 590236 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1206467 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1080967 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6058. Min Act: -0.0000

Data Index: 498416 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.8883. Min Range: -0.8883

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1025020 (C4 (Web Text))

Max Activating Token Index: 968