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

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

Neuron 4682 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.2987. Min Act: -0.0000

Data Index: 118812 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.1280. Min Act: -0.0000

Data Index: 265251 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.0764. Min Act: -0.0000

Data Index: 316929 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.0632. Min Act: -0.0000

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.1563. Min Act: -0.0000

Data Index: 592982 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.0992. Min Act: -0.0000

Data Index: 399680 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1266768 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1231831 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.0064. Min Act: -0.0000

Data Index: 116433 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9269. Min Act: -0.0000

Data Index: 498939 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9329. Min Act: -0.0000

Data Index: 1095859 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1268618 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1440110 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8984. Min Act: -0.0000

Data Index: 745194 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9300. Min Act: -0.0000

Data Index: 169479 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1126114 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1188057 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1267761 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8703. Min Act: -0.0000

Data Index: 973298 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1357278 (C4 (Web Text))

Max Activating Token Index: 372