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

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

Neuron 3148 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.6139. Min Act: -0.0000

Data Index: 226258 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0738. Min Act: -0.0000

Data Index: 911898 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0705. Min Act: -0.0000

Data Index: 183294 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0436. Min Act: -0.0000

Data Index: 976461 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0633. Min Act: -0.0000

Data Index: 812928 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0575. Min Act: -0.0000

Data Index: 971717 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1230860 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0498. Min Act: -0.0000

Data Index: 302429 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.6139. Min Range: -1.6139

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1141801 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9661. Min Act: -0.0000

Data Index: 419545 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9905. Min Act: -0.0000

Data Index: 81837 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9599. Min Act: -0.0000

Data Index: 871571 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1077874 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1064406 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9671. Min Act: -0.0000

Data Index: 425663 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9711. Min Act: -0.0000

Data Index: 597043 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9683. Min Act: -0.0000

Data Index: 564875 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9385. Min Act: -0.0000

Data Index: 45003 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.9333. Min Act: -0.0000

Data Index: 385676 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.6139. Min Range: -1.6139

Max Act: 0.8889. Min Act: -0.0000

Data Index: 841811 (C4 (Web Text))

Max Activating Token Index: 723