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

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

Neuron 1780 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3036. Min Range: -4.3036

Max Act: 4.2418. Min Act: -0.0000

Data Index: 299588 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 4.3036. Min Range: -4.3036

Max Act: 4.3036. Min Act: -0.0000

Data Index: 448966 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.9663. Min Act: -0.0000

Data Index: 997466 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.9664. Min Act: -0.0000

Data Index: 196398 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.6314. Min Act: -0.0000

Data Index: 145981 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.7602. Min Act: -0.0000

Data Index: 730746 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.6584. Min Act: -0.0000

Data Index: 1064114 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.6684. Min Act: -0.0000

Data Index: 1270160 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.4811. Min Act: -0.0000

Data Index: 998300 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.6406. Min Act: -0.0000

Data Index: 988086 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.5865. Min Act: -0.0000

Data Index: 1249321 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.5800. Min Act: -0.0000

Data Index: 441185 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.5901. Min Act: -0.0000

Data Index: 857135 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.5841. Min Act: -0.0000

Data Index: 869338 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.5369. Min Act: -0.0000

Data Index: 1121796 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.5093. Min Act: -0.0000

Data Index: 902567 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.5013. Min Act: -0.0000

Data Index: 304227 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.5119. Min Act: -0.0000

Data Index: 295633 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.4809. Min Act: -0.0000

Data Index: 1175833 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 4.3036. Min Range: -4.3036

Max Act: 3.4738. Min Act: -0.0000

Data Index: 500709 (C4 (Web Text))

Max Activating Token Index: 565