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

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

Neuron 237 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: 1.6682. Min Range: -1.6682

Max Act: 1.6682. Min Act: -0.0000

Data Index: 1045525 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.5739. Min Act: -0.0000

Data Index: 929733 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3812. Min Act: -0.0000

Data Index: 629769 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3568. Min Act: -0.0000

Data Index: 580849 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3821. Min Act: -0.0000

Data Index: 701347 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2588. Min Act: -0.0000

Data Index: 972319 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2054. Min Act: -0.0001

Data Index: 465641 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0567. Min Act: -0.0001

Data Index: 1014061 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1175683 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0879. Min Act: -0.0001

Data Index: 1068318 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9222. Min Act: -0.0000

Data Index: 389993 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1056843 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0105. Min Act: -0.0001

Data Index: 1249496 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.8785. Min Act: -0.0000

Data Index: 691490 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.7693. Min Act: -0.0000

Data Index: 805260 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1079897 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0730. Min Act: -0.0000

Data Index: 769406 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.6682. Min Range: -1.6682

Max Act: 0.9211. Min Act: -0.0000

Data Index: 124055 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.1229. Min Act: -0.0000

Data Index: 288119 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.0473. Min Act: -0.0000

Data Index: 403584 (C4 (Web Text))

Max Activating Token Index: 682