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

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

Neuron 900 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: 3.2713. Min Range: -3.2713

Max Act: 3.2571. Min Act: -0.0001

Data Index: 1153881 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 3.2713. Min Range: -3.2713

Max Act: 3.1663. Min Act: -0.0001

Data Index: 1148655 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.2713. Min Range: -3.2713

Max Act: 3.2713. Min Act: -0.0001

Data Index: 508532 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 3.2713. Min Range: -3.2713

Max Act: 3.0757. Min Act: -0.0001

Data Index: 269069 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.7922. Min Act: -0.0001

Data Index: 469402 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.4882. Min Act: -0.0001

Data Index: 1006025 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.7362. Min Act: -0.0001

Data Index: 778277 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.6312. Min Act: -0.0001

Data Index: 697838 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.7009. Min Act: -0.0001

Data Index: 808478 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.9133. Min Act: -0.0001

Data Index: 885619 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.9427. Min Act: -0.0001

Data Index: 1156763 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 3.2713. Min Range: -3.2713

Max Act: 3.0639. Min Act: -0.0001

Data Index: 625605 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.7585. Min Act: -0.0001

Data Index: 743172 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.6074. Min Act: -0.0001

Data Index: 84762 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.5769. Min Act: -0.0001

Data Index: 816996 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.9157. Min Act: -0.0001

Data Index: 1115446 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.6513. Min Act: -0.0001

Data Index: 1178856 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.8610. Min Act: -0.0001

Data Index: 117178 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.9789. Min Act: -0.0001

Data Index: 674655 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 3.2713. Min Range: -3.2713

Max Act: 2.6563. Min Act: -0.0001

Data Index: 58423 (C4 (Web Text))

Max Activating Token Index: 967