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

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

Neuron 3626 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0678. Min Act: -0.0003

Data Index: 856574 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0694. Min Act: -0.0003

Data Index: 457074 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1294284 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1268898 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0660. Min Act: -0.0003

Data Index: 187315 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0617. Min Act: -0.0003

Data Index: 207555 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0654. Min Act: -0.0003

Data Index: 595634 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1078117 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0578. Min Act: -0.0003

Data Index: 896758 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0635. Min Act: -0.0003

Data Index: 920375 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0613. Min Act: -0.0003

Data Index: 873452 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0592. Min Act: -0.0003

Data Index: 835136 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1113099 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1348942 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0567. Min Act: -0.0003

Data Index: 566870 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0589. Min Act: -0.0003

Data Index: 403939 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0562. Min Act: -0.0003

Data Index: 354272 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0575. Min Act: -0.0003

Data Index: 90638 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1060937 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0565. Min Act: -0.0003

Data Index: 118048 (C4 (Web Text))

Max Activating Token Index: 892