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

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

Neuron 696 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: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0005

Data Index: 275431 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0541. Min Act: -0.0005

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0548. Min Act: -0.0005

Data Index: 954152 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0542. Min Act: -0.0005

Data Index: 80009 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0500. Min Act: -0.0005

Data Index: 499916 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0508. Min Act: -0.0005

Data Index: 1308776 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0492. Min Act: -0.0005

Data Index: 758351 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0457. Min Act: -0.0005

Data Index: 92643 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0477. Min Act: -0.0005

Data Index: 1261221 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0445. Min Act: -0.0005

Data Index: 268042 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0428. Min Act: -0.0005

Data Index: 536334 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0468. Min Act: -0.0005

Data Index: 1253107 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0422. Min Act: -0.0005

Data Index: 564397 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0437. Min Act: -0.0005

Data Index: 1313931 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0424. Min Act: -0.0005

Data Index: 431080 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0402. Min Act: -0.0005

Data Index: 59097 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0395. Min Act: -0.0005

Data Index: 155911 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0419. Min Act: -0.0005

Data Index: 358925 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0403. Min Act: -0.0005

Data Index: 1090396 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0411. Min Act: -0.0005

Data Index: 1313100 (C4 (Web Text))

Max Activating Token Index: 199