Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2694 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0478. Min Act: -0.0000

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0000

Data Index: 423163 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0428. Min Act: -0.0000

Data Index: 172161 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1291463 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0410. Min Act: -0.0000

Data Index: 120087 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0415. Min Act: -0.0000

Data Index: 984667 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0423. Min Act: -0.0000

Data Index: 795581 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1538120 (Python Code)

Max Activating Token Index: 384

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0376. Min Act: -0.0000

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1055212 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0366. Min Act: -0.0000

Data Index: 518838 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0372. Min Act: -0.0000

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0322. Min Act: -0.0000

Data Index: 113177 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1446704 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0331. Min Act: -0.0000

Data Index: 307652 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0340. Min Act: -0.0000

Data Index: 927953 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0318. Min Act: -0.0000

Data Index: 868820 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0360. Min Act: -0.0000

Data Index: 796813 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1285159 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0299. Min Act: -0.0000

Data Index: 71895 (C4 (Web Text))

Max Activating Token Index: 207