Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3787 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.1077. Min Act: -0.0001

Data Index: 452918 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.1077. Min Range: -1.1077

Max Act: 1.0850. Min Act: -0.0001

Data Index: 141728 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9129. Min Act: -0.0001

Data Index: 498457 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9731. Min Act: -0.0001

Data Index: 886861 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9653. Min Act: -0.0001

Data Index: 1104329 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.9155. Min Act: -0.0001

Data Index: 210279 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8642. Min Act: -0.0001

Data Index: 1011856 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8782. Min Act: -0.0001

Data Index: 1193668 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8577. Min Act: -0.0001

Data Index: 721003 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8683. Min Act: -0.0001

Data Index: 1255057 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8396. Min Act: -0.0001

Data Index: 1279027 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.7733. Min Act: -0.0001

Data Index: 26866 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1111615 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8499. Min Act: -0.0001

Data Index: 792550 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.7733. Min Act: -0.0001

Data Index: 1245977 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.7056. Min Act: -0.0001

Data Index: 520665 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.7641. Min Act: -0.0001

Data Index: 444668 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8120. Min Act: -0.0001

Data Index: 762247 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.8079. Min Act: -0.0001

Data Index: 37767 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 1.1077. Min Range: -1.1077

Max Act: 0.7577. Min Act: -0.0001

Data Index: 995544 (C4 (Web Text))

Max Activating Token Index: 441