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

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

Neuron 3944 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0002

Data Index: 30675 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0683. Min Act: -0.0002

Data Index: 855595 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0657. Min Act: -0.0002

Data Index: 181114 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0553. Min Act: -0.0002

Data Index: 855148 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1327832 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0556. Min Act: -0.0002

Data Index: 853250 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1177170 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0624. Min Act: -0.0002

Data Index: 271339 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0550. Min Act: -0.0002

Data Index: 762837 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1120636 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0469. Min Act: -0.0002

Data Index: 640264 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0452. Min Act: -0.0002

Data Index: 253278 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0485. Min Act: -0.0002

Data Index: 608911 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1179658 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1094137 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0479. Min Act: -0.0002

Data Index: 596985 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1339397 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1070964 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0469. Min Act: -0.0002

Data Index: 17245 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1300583 (C4 (Web Text))

Max Activating Token Index: 737