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

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

Neuron 311 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0001

Data Index: 250209 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1142686 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0709. Min Act: -0.0001

Data Index: 596101 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1096539 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1163114 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1078852 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1042200 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1173756 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1454476 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1447958 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1497119 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1616333 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0609. Min Act: -0.0001

Data Index: 190245 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0588. Min Act: -0.0001

Data Index: 655928 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0628. Min Act: -0.0001

Data Index: 503708 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0580. Min Act: -0.0001

Data Index: 291521 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1577386 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1571948 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0592. Min Act: -0.0001

Data Index: 681817 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0613. Min Act: -0.0001

Data Index: 141989 (C4 (Web Text))

Max Activating Token Index: 580