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

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

Neuron 3814 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.1778. Min Act: -0.0000

Data Index: 621545 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.9158. Min Act: -0.0000

Data Index: 911666 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.6819. Min Act: -0.0000

Data Index: 439529 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0294. Min Act: -0.0000

Data Index: 1343524 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.6684. Min Act: -0.0000

Data Index: 881709 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.8022. Min Act: -0.0000

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.7568. Min Act: -0.0000

Data Index: 318418 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.6922. Min Act: -0.0000

Data Index: 419586 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.8428. Min Act: -0.0000

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.4904. Min Act: -0.0000

Data Index: 1296212 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.4105. Min Act: -0.0000

Data Index: 927933 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.6743. Min Act: -0.0000

Data Index: 349105 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.3634. Min Act: -0.0000

Data Index: 1229649 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.4662. Min Act: -0.0000

Data Index: 1187312 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.4547. Min Act: -0.0000

Data Index: 878328 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.5494. Min Act: -0.0000

Data Index: 927610 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.1602. Min Act: -0.0000

Data Index: 1175257 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.1359. Min Act: -0.0000

Data Index: 748249 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.0544. Min Act: -0.0000

Data Index: 268403 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 4.1778. Min Range: -4.1778

Max Act: 3.0330. Min Act: -0.0000

Data Index: 471022 (C4 (Web Text))

Max Activating Token Index: 193