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

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

Neuron 1747 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.8575. Min Act: -0.0000

Data Index: 1529059 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.6044. Min Act: -0.0000

Data Index: 1643066 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.3561. Min Act: -0.0000

Data Index: 1443747 (Python Code)

Max Activating Token Index: 407

Text #3

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.2512. Min Act: -0.0000

Data Index: 1473399 (Python Code)

Max Activating Token Index: 782

Text #4

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.2496. Min Act: -0.0000

Data Index: 1568079 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.3104. Min Act: -0.0000

Data Index: 1425953 (Python Code)

Max Activating Token Index: 903

Text #6

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.1519. Min Act: -0.0000

Data Index: 1371651 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.3050. Min Act: -0.0000

Data Index: 1572841 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.0740. Min Act: -0.0000

Data Index: 1476954 (Python Code)

Max Activating Token Index: 629

Text #9

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.2533. Min Act: -0.0000

Data Index: 1536399 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.3915. Min Act: -0.0000

Data Index: 1442577 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.0247. Min Act: -0.0000

Data Index: 1462830 (Python Code)

Max Activating Token Index: 590

Text #12

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.2024. Min Act: -0.0000

Data Index: 1475640 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 5.8575. Min Range: -5.8575

Max Act: 4.9824. Min Act: -0.0000

Data Index: 1414677 (Python Code)

Max Activating Token Index: 403

Text #14

Max Range: 5.8575. Min Range: -5.8575

Max Act: 4.9692. Min Act: -0.0000

Data Index: 1593957 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.1186. Min Act: -0.0000

Data Index: 1553534 (Python Code)

Max Activating Token Index: 884

Text #16

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.1004. Min Act: -0.0000

Data Index: 1461202 (Python Code)

Max Activating Token Index: 746

Text #17

Max Range: 5.8575. Min Range: -5.8575

Max Act: 4.9349. Min Act: -0.0000

Data Index: 1499272 (Python Code)

Max Activating Token Index: 357

Text #18

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.0951. Min Act: -0.0000

Data Index: 1649770 (Python Code)

Max Activating Token Index: 921

Text #19

Max Range: 5.8575. Min Range: -5.8575

Max Act: 5.0823. Min Act: -0.0000

Data Index: 1469279 (Python Code)

Max Activating Token Index: 816