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

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

Neuron 951 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0006

Data Index: 662414 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0340. Min Act: -0.0006

Data Index: 482702 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0331. Min Act: -0.0006

Data Index: 920699 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1016775 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0297. Min Act: -0.0006

Data Index: 635357 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0341. Min Act: -0.0006

Data Index: 934879 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0284. Min Act: -0.0006

Data Index: 656551 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0315. Min Act: -0.0006

Data Index: 476006 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0323. Min Act: -0.0006

Data Index: 722198 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1110101 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0328. Min Act: -0.0006

Data Index: 727788 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0320. Min Act: -0.0006

Data Index: 753160 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0324. Min Act: -0.0006

Data Index: 880784 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0311. Min Act: -0.0006

Data Index: 307032 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0328. Min Act: -0.0006

Data Index: 644321 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0305. Min Act: -0.0006

Data Index: 995389 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1112096 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0305. Min Act: -0.0006

Data Index: 80276 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0308. Min Act: -0.0006

Data Index: 666918 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1332746 (C4 (Web Text))

Max Activating Token Index: 357