Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 478 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0005

Data Index: 1161533 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0677. Min Act: -0.0005

Data Index: 1110670 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0655. Min Act: -0.0005

Data Index: 187251 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0660. Min Act: -0.0005

Data Index: 121512 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0614. Min Act: -0.0005

Data Index: 1102853 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0611. Min Act: -0.0005

Data Index: 319219 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0627. Min Act: -0.0005

Data Index: 161253 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0569. Min Act: -0.0005

Data Index: 429217 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0602. Min Act: -0.0005

Data Index: 1161813 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0576. Min Act: -0.0005

Data Index: 260650 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0604. Min Act: -0.0005

Data Index: 176968 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0601. Min Act: -0.0005

Data Index: 1028993 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0558. Min Act: -0.0005

Data Index: 1139298 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0594. Min Act: -0.0005

Data Index: 1312308 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0579. Min Act: -0.0005

Data Index: 912359 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0606. Min Act: -0.0005

Data Index: 1208908 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0543. Min Act: -0.0005

Data Index: 71439 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0582. Min Act: -0.0005

Data Index: 1155321 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0556. Min Act: -0.0005

Data Index: 525716 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0572. Min Act: -0.0005

Data Index: 124848 (C4 (Web Text))

Max Activating Token Index: 187