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

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

Neuron 4213 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2413. Min Range: -4.2413

Max Act: 4.2413. Min Act: -0.0000

Data Index: 1612890 (Python Code)

Max Activating Token Index: 726

Text #1

Max Range: 4.2413. Min Range: -4.2413

Max Act: 4.2041. Min Act: -0.0000

Data Index: 1501270 (Python Code)

Max Activating Token Index: 794

Text #2

Max Range: 4.2413. Min Range: -4.2413

Max Act: 4.1770. Min Act: -0.0001

Data Index: 1601022 (Python Code)

Max Activating Token Index: 379

Text #3

Max Range: 4.2413. Min Range: -4.2413

Max Act: 4.0365. Min Act: -0.0001

Data Index: 1374665 (Python Code)

Max Activating Token Index: 595

Text #4

Max Range: 4.2413. Min Range: -4.2413

Max Act: 4.0298. Min Act: -0.0001

Data Index: 1449627 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.9987. Min Act: -0.0000

Data Index: 1584288 (Python Code)

Max Activating Token Index: 990

Text #6

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.8440. Min Act: -0.0001

Data Index: 1625043 (Python Code)

Max Activating Token Index: 494

Text #7

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.8141. Min Act: -0.0001

Data Index: 1454177 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.9357. Min Act: -0.0000

Data Index: 1487011 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.5967. Min Act: -0.0001

Data Index: 1488737 (Python Code)

Max Activating Token Index: 441

Text #10

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.7440. Min Act: -0.0001

Data Index: 1553565 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.6614. Min Act: -0.0001

Data Index: 1473003 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.8130. Min Act: -0.0000

Data Index: 1484990 (Python Code)

Max Activating Token Index: 443

Text #13

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.6340. Min Act: -0.0001

Data Index: 1558826 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.5995. Min Act: -0.0001

Data Index: 1635813 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.3826. Min Act: -0.0000

Data Index: 1537897 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.4595. Min Act: -0.0001

Data Index: 1463887 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.1539. Min Act: -0.0000

Data Index: 1627491 (Python Code)

Max Activating Token Index: 837

Text #18

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.4528. Min Act: -0.0001

Data Index: 1520182 (Python Code)

Max Activating Token Index: 479

Text #19

Max Range: 4.2413. Min Range: -4.2413

Max Act: 3.4209. Min Act: -0.0001

Data Index: 1437892 (Python Code)

Max Activating Token Index: 216