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

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

Neuron 912 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.8490. Min Act: -0.0001

Data Index: 607046 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.8012. Min Act: -0.0001

Data Index: 654653 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.8103. Min Act: -0.0001

Data Index: 702664 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7845. Min Act: -0.0001

Data Index: 800001 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7746. Min Act: -0.0001

Data Index: 779437 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.8156. Min Act: -0.0001

Data Index: 670093 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7812. Min Act: -0.0001

Data Index: 1302172 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7645. Min Act: -0.0001

Data Index: 814871 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7797. Min Act: -0.0001

Data Index: 439946 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7751. Min Act: -0.0001

Data Index: 510875 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7479. Min Act: -0.0001

Data Index: 119955 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7752. Min Act: -0.0001

Data Index: 1214225 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7720. Min Act: -0.0001

Data Index: 99699 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7713. Min Act: -0.0001

Data Index: 511001 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1224694 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7113. Min Act: -0.0001

Data Index: 1339596 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1191778 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7653. Min Act: -0.0001

Data Index: 815428 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7193. Min Act: -0.0001

Data Index: 241699 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.8490. Min Range: -0.8490

Max Act: 0.7346. Min Act: -0.0001

Data Index: 1031521 (C4 (Web Text))

Max Activating Token Index: 589