Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3546 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3550. Min Range: -4.3550

Max Act: 4.3550. Min Act: -0.0000

Data Index: 1458715 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 4.3550. Min Range: -4.3550

Max Act: 4.1364. Min Act: -0.0000

Data Index: 1432476 (Python Code)

Max Activating Token Index: 394

Text #2

Max Range: 4.3550. Min Range: -4.3550

Max Act: 4.1751. Min Act: -0.0001

Data Index: 1594372 (Python Code)

Max Activating Token Index: 153

Text #3

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.9593. Min Act: -0.0000

Data Index: 1486574 (Python Code)

Max Activating Token Index: 662

Text #4

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.9766. Min Act: -0.0000

Data Index: 1510691 (Python Code)

Max Activating Token Index: 550

Text #5

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.9024. Min Act: -0.0000

Data Index: 1380868 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.6338. Min Act: -0.0000

Data Index: 1638557 (Python Code)

Max Activating Token Index: 308

Text #7

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.7875. Min Act: -0.0000

Data Index: 1585446 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.7770. Min Act: -0.0000

Data Index: 1435780 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.7460. Min Act: -0.0000

Data Index: 1508473 (Python Code)

Max Activating Token Index: 348

Text #10

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.7602. Min Act: -0.0000

Data Index: 1415331 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.5934. Min Act: -0.0000

Data Index: 1420430 (Python Code)

Max Activating Token Index: 805

Text #12

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.8557. Min Act: -0.0000

Data Index: 1385537 (Python Code)

Max Activating Token Index: 393

Text #13

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.6232. Min Act: -0.0000

Data Index: 1651037 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.6285. Min Act: -0.0000

Data Index: 1490784 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.6138. Min Act: -0.0000

Data Index: 1434446 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.4199. Min Act: -0.0000

Data Index: 1634829 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.5799. Min Act: -0.0000

Data Index: 1387900 (Python Code)

Max Activating Token Index: 299

Text #18

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.7450. Min Act: -0.0000

Data Index: 1455038 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 4.3550. Min Range: -4.3550

Max Act: 3.4073. Min Act: -0.0000

Data Index: 1433187 (Python Code)

Max Activating Token Index: 958