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

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

Neuron 1072 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: 0.0374. Min Range: -0.0374

Max Act: 0.0365. Min Act: -0.0005

Data Index: 1385332 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0005

Data Index: 1618741 (Python Code)

Max Activating Token Index: 557

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0359. Min Act: -0.0005

Data Index: 1354457 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0368. Min Act: -0.0005

Data Index: 1565153 (Python Code)

Max Activating Token Index: 736

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0337. Min Act: -0.0005

Data Index: 1534814 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0331. Min Act: -0.0005

Data Index: 1473854 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0317. Min Act: -0.0005

Data Index: 437118 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0323. Min Act: -0.0005

Data Index: 1393112 (Python Code)

Max Activating Token Index: 319

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0344. Min Act: -0.0005

Data Index: 635706 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1377464 (Python Code)

Max Activating Token Index: 489

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1626201 (Python Code)

Max Activating Token Index: 604

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1474007 (Python Code)

Max Activating Token Index: 846

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0324. Min Act: -0.0005

Data Index: 744632 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0329. Min Act: -0.0005

Data Index: 1563490 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0323. Min Act: -0.0005

Data Index: 1609433 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0315. Min Act: -0.0005

Data Index: 1259632 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0290. Min Act: -0.0005

Data Index: 11807 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0306. Min Act: -0.0005

Data Index: 1617129 (Python Code)

Max Activating Token Index: 340

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0308. Min Act: -0.0005

Data Index: 1503772 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0323. Min Act: -0.0005

Data Index: 1426006 (Python Code)

Max Activating Token Index: 454