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

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

Neuron 5801 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: 0.3071. Min Range: -0.3071

Max Act: 0.3071. Min Act: -0.0000

Data Index: 417899 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2902. Min Act: -0.0000

Data Index: 716055 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2921. Min Act: -0.0000

Data Index: 679864 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2723. Min Act: -0.0000

Data Index: 507126 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2907. Min Act: -0.0000

Data Index: 295942 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2789. Min Act: -0.0000

Data Index: 291816 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2632. Min Act: -0.0000

Data Index: 85606 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2546. Min Act: -0.0000

Data Index: 177310 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1063028 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2507. Min Act: -0.0000

Data Index: 79109 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2677. Min Act: -0.0000

Data Index: 537522 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2587. Min Act: -0.0000

Data Index: 451412 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2555. Min Act: -0.0000

Data Index: 30973 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2544. Min Act: -0.0000

Data Index: 568389 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1267831 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1023228 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2456. Min Act: -0.0000

Data Index: 166891 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2493. Min Act: -0.0000

Data Index: 210621 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2429. Min Act: -0.0000

Data Index: 513516 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.3071. Min Range: -0.3071

Max Act: 0.2253. Min Act: -0.0000

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 974