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

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

Neuron 4680 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0767. Min Range: -4.0767

Max Act: 4.0767. Min Act: -0.0000

Data Index: 1551467 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 4.0767. Min Range: -4.0767

Max Act: 3.1984. Min Act: -0.0000

Data Index: 1583839 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 4.0767. Min Range: -4.0767

Max Act: 3.0172. Min Act: -0.0000

Data Index: 1605064 (Python Code)

Max Activating Token Index: 673

Text #3

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.8691. Min Act: -0.0000

Data Index: 1484965 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.8487. Min Act: -0.0000

Data Index: 1478044 (Python Code)

Max Activating Token Index: 811

Text #5

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.5038. Min Act: -0.0000

Data Index: 1521953 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.7706. Min Act: -0.0000

Data Index: 1594382 (Python Code)

Max Activating Token Index: 371

Text #7

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.5548. Min Act: -0.0000

Data Index: 1432674 (Python Code)

Max Activating Token Index: 820

Text #8

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.5371. Min Act: -0.0000

Data Index: 1557364 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.4136. Min Act: -0.0000

Data Index: 1435026 (Python Code)

Max Activating Token Index: 917

Text #10

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.5397. Min Act: -0.0000

Data Index: 1373287 (Python Code)

Max Activating Token Index: 780

Text #11

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.3923. Min Act: -0.0000

Data Index: 1609795 (Python Code)

Max Activating Token Index: 802

Text #12

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.5061. Min Act: -0.0000

Data Index: 1410775 (Python Code)

Max Activating Token Index: 372

Text #13

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.4827. Min Act: -0.0000

Data Index: 1503487 (Python Code)

Max Activating Token Index: 1008

Text #14

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.5819. Min Act: -0.0000

Data Index: 1390278 (Python Code)

Max Activating Token Index: 643

Text #15

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.4660. Min Act: -0.0000

Data Index: 1656383 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.3275. Min Act: -0.0000

Data Index: 1607923 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.5344. Min Act: -0.0000

Data Index: 1629562 (Python Code)

Max Activating Token Index: 686

Text #18

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.3390. Min Act: -0.0000

Data Index: 1459669 (Python Code)

Max Activating Token Index: 566

Text #19

Max Range: 4.0767. Min Range: -4.0767

Max Act: 2.1033. Min Act: -0.0000

Data Index: 1511223 (Python Code)

Max Activating Token Index: 971