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

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

Neuron 4998 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.1681. Min Act: -0.0001

Data Index: 1411445 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1473050 (Python Code)

Max Activating Token Index: 85

Text #2

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.1778. Min Act: -0.0001

Data Index: 1577724 (Python Code)

Max Activating Token Index: 617

Text #3

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.1395. Min Act: -0.0000

Data Index: 129136 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.0643. Min Act: -0.0000

Data Index: 863343 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.1270. Min Act: -0.0000

Data Index: 21480 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1251464 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.9683. Min Act: -0.0000

Data Index: 750361 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.0085. Min Act: -0.0000

Data Index: 411167 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1258035 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.0353. Min Act: -0.0000

Data Index: 974584 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1183592 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.9951. Min Act: -0.0000

Data Index: 456540 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1058722 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.9702. Min Act: -0.0000

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.9543. Min Act: -0.0000

Data Index: 502724 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.9293. Min Act: -0.0000

Data Index: 10486 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 1.1778. Min Range: -1.1778

Max Act: 1.0138. Min Act: -0.0000

Data Index: 455802 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.9491. Min Act: -0.0000

Data Index: 833099 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.1778. Min Range: -1.1778

Max Act: 0.8756. Min Act: -0.0000

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 801