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

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

Neuron 226 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1081369 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0866. Min Act: -0.0001

Data Index: 17395 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0735. Min Act: -0.0001

Data Index: 23773 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0715. Min Act: -0.0001

Data Index: 252254 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0764. Min Act: -0.0001

Data Index: 390101 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1301262 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0763. Min Act: -0.0001

Data Index: 568557 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1081550 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1001785 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0650. Min Act: -0.0001

Data Index: 207095 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0676. Min Act: -0.0001

Data Index: 507821 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0672. Min Act: -0.0001

Data Index: 25185 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0667. Min Act: -0.0001

Data Index: 302825 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0668. Min Act: -0.0001

Data Index: 475391 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0685. Min Act: -0.0001

Data Index: 848492 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0648. Min Act: -0.0001

Data Index: 69719 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1303631 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0588. Min Act: -0.0001

Data Index: 673495 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0623. Min Act: -0.0001

Data Index: 234409 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0621. Min Act: -0.0001

Data Index: 638086 (C4 (Web Text))

Max Activating Token Index: 495