Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 447 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.8460. Min Act: -0.0000

Data Index: 114274 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1310229 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.8183. Min Act: -0.0000

Data Index: 980948 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7763. Min Act: -0.0000

Data Index: 442694 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7194. Min Act: -0.0001

Data Index: 415959 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7666. Min Act: -0.0000

Data Index: 895656 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.8308. Min Act: -0.0000

Data Index: 863264 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7905. Min Act: -0.0000

Data Index: 509453 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7740. Min Act: -0.0000

Data Index: 741749 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7200. Min Act: -0.0000

Data Index: 143184 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7379. Min Act: -0.0000

Data Index: 969964 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7140. Min Act: -0.0000

Data Index: 640848 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.7260. Min Act: -0.0000

Data Index: 865541 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.6740. Min Act: -0.0000

Data Index: 734135 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.6479. Min Act: -0.0000

Data Index: 834717 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1330865 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.6689. Min Act: -0.0001

Data Index: 422103 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.5665. Min Act: -0.0000

Data Index: 574586 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1347598 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.8460. Min Range: -0.8460

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1089949 (C4 (Web Text))

Max Activating Token Index: 184