Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2810 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1399514 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3834. Min Act: -0.0001

Data Index: 1616424 (Python Code)

Max Activating Token Index: 648

Text #2

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3789. Min Act: 0.0000

Data Index: 1591733 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3749. Min Act: -0.0001

Data Index: 1494018 (Python Code)

Max Activating Token Index: 367

Text #4

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1596442 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3557. Min Act: -0.0001

Data Index: 1396354 (Python Code)

Max Activating Token Index: 689

Text #6

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1597226 (Python Code)

Max Activating Token Index: 352

Text #7

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3486. Min Act: -0.0001

Data Index: 1456986 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1362388 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3584. Min Act: -0.0001

Data Index: 1584468 (Python Code)

Max Activating Token Index: 545

Text #10

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3554. Min Act: -0.0001

Data Index: 1419387 (Python Code)

Max Activating Token Index: 303

Text #11

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3406. Min Act: -0.0001

Data Index: 1377628 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1572653 (Python Code)

Max Activating Token Index: 674

Text #13

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1582151 (Python Code)

Max Activating Token Index: 439

Text #14

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1564395 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1471669 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1404385 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3089. Min Act: -0.0001

Data Index: 1360711 (Python Code)

Max Activating Token Index: 392

Text #18

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3299. Min Act: -0.0001

Data Index: 1644874 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 0.4001. Min Range: -0.4001

Max Act: 0.3281. Min Act: -0.0001

Data Index: 1551161 (Python Code)

Max Activating Token Index: 40