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

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

Neuron 540 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: 0.4550. Min Range: -0.4550

Max Act: 0.4100. Min Act: -0.0000

Data Index: 513707 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.4550. Min Act: -0.0000

Data Index: 836498 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3950. Min Act: -0.0000

Data Index: 415348 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3971. Min Act: -0.0000

Data Index: 716993 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1262578 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3767. Min Act: -0.0000

Data Index: 138143 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3727. Min Act: -0.0000

Data Index: 392163 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3702. Min Act: -0.0000

Data Index: 422409 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3857. Min Act: -0.0000

Data Index: 644691 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3935. Min Act: -0.0000

Data Index: 112373 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3964. Min Act: -0.0000

Data Index: 588782 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1066060 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3902. Min Act: -0.0000

Data Index: 643276 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3798. Min Act: -0.0000

Data Index: 780837 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3887. Min Act: -0.0000

Data Index: 492543 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3763. Min Act: -0.0000

Data Index: 451379 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3764. Min Act: -0.0000

Data Index: 231482 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3958. Min Act: -0.0000

Data Index: 203203 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3838. Min Act: -0.0000

Data Index: 902463 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3694. Min Act: -0.0000

Data Index: 520455 (C4 (Web Text))

Max Activating Token Index: 389