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

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

Neuron 717 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: 0.0456. Min Range: -0.0456

Max Act: 0.0437. Min Act: -0.0005

Data Index: 386544 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0451. Min Act: -0.0005

Data Index: 379677 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0005

Data Index: 916253 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0398. Min Act: -0.0004

Data Index: 1315773 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0409. Min Act: -0.0005

Data Index: 536943 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0413. Min Act: -0.0005

Data Index: 944991 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0404. Min Act: -0.0005

Data Index: 372542 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0420. Min Act: -0.0005

Data Index: 1312492 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0402. Min Act: -0.0005

Data Index: 766904 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0418. Min Act: -0.0005

Data Index: 285574 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0411. Min Act: -0.0005

Data Index: 1189331 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0391. Min Act: -0.0005

Data Index: 192803 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0383. Min Act: -0.0005

Data Index: 300644 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0397. Min Act: -0.0005

Data Index: 349997 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0403. Min Act: -0.0005

Data Index: 349068 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0403. Min Act: -0.0005

Data Index: 1073077 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0361. Min Act: -0.0005

Data Index: 49634 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0394. Min Act: -0.0005

Data Index: 504608 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0368. Min Act: -0.0005

Data Index: 786870 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0379. Min Act: -0.0005

Data Index: 91823 (C4 (Web Text))

Max Activating Token Index: 98