Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3988 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1592433 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1584365 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1470434 (Python Code)

Max Activating Token Index: 242

Text #3

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1578191 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1504754 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1402950 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1486921 (Python Code)

Max Activating Token Index: 689

Text #7

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1601587 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1415331 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1615193 (Python Code)

Max Activating Token Index: 988

Text #10

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1582914 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1613290 (Python Code)

Max Activating Token Index: 630

Text #12

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1604663 (Python Code)

Max Activating Token Index: 806

Text #13

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1469893 (Python Code)

Max Activating Token Index: 998

Text #14

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1552178 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1393882 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1459291 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1451807 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1506213 (Python Code)

Max Activating Token Index: 425

Text #19

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1504573 (Python Code)

Max Activating Token Index: 711