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

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

Neuron 1001 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.5672. Min Act: -0.0000

Data Index: 1382048 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3530. Min Act: -0.0001

Data Index: 1535981 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3315. Min Act: -0.0000

Data Index: 1628005 (Python Code)

Max Activating Token Index: 828

Text #3

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3964. Min Act: -0.0000

Data Index: 1513762 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.1728. Min Act: -0.0000

Data Index: 1384286 (Python Code)

Max Activating Token Index: 186

Text #5

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.4498. Min Act: -0.0000

Data Index: 1628659 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.2049. Min Act: -0.0000

Data Index: 1542039 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.1303. Min Act: -0.0000

Data Index: 1464543 (Python Code)

Max Activating Token Index: 515

Text #8

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.2611. Min Act: -0.0001

Data Index: 1405992 (Python Code)

Max Activating Token Index: 899

Text #9

Max Range: 3.5672. Min Range: -3.5672

Max Act: 2.9711. Min Act: -0.0000

Data Index: 1558108 (Python Code)

Max Activating Token Index: 456

Text #10

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.2438. Min Act: -0.0001

Data Index: 1452490 (Python Code)

Max Activating Token Index: 339

Text #11

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.0700. Min Act: -0.0000

Data Index: 1638652 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 3.5672. Min Range: -3.5672

Max Act: 2.9581. Min Act: -0.0001

Data Index: 1392507 (Python Code)

Max Activating Token Index: 674

Text #13

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.0237. Min Act: -0.0000

Data Index: 1566986 (Python Code)

Max Activating Token Index: 413

Text #14

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.0154. Min Act: -0.0000

Data Index: 1640438 (Python Code)

Max Activating Token Index: 607

Text #15

Max Range: 3.5672. Min Range: -3.5672

Max Act: 2.8300. Min Act: -0.0001

Data Index: 1516103 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 3.5672. Min Range: -3.5672

Max Act: 2.8341. Min Act: -0.0001

Data Index: 1652049 (Python Code)

Max Activating Token Index: 150

Text #17

Max Range: 3.5672. Min Range: -3.5672

Max Act: 2.9898. Min Act: -0.0001

Data Index: 1487285 (Python Code)

Max Activating Token Index: 334

Text #18

Max Range: 3.5672. Min Range: -3.5672

Max Act: 2.8161. Min Act: -0.0000

Data Index: 1508827 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.0318. Min Act: -0.0000

Data Index: 1577156 (Python Code)

Max Activating Token Index: 704