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

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

Neuron 1311 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.9317. Min Act: -0.0000

Data Index: 1557826 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 2.0928. Min Range: -2.0928

Max Act: 2.0928. Min Act: -0.0000

Data Index: 1478165 (Python Code)

Max Activating Token Index: 49

Text #2

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.7631. Min Act: -0.0000

Data Index: 1590260 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.8104. Min Act: -0.0000

Data Index: 1456139 (Python Code)

Max Activating Token Index: 819

Text #4

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.9002. Min Act: -0.0000

Data Index: 1485507 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1620771 (Python Code)

Max Activating Token Index: 408

Text #6

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.6689. Min Act: -0.0000

Data Index: 1621920 (Python Code)

Max Activating Token Index: 379

Text #7

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.6807. Min Act: -0.0000

Data Index: 1566809 (Python Code)

Max Activating Token Index: 442

Text #8

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.6780. Min Act: -0.0000

Data Index: 1641590 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.5669. Min Act: -0.0000

Data Index: 1430385 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.6494. Min Act: -0.0000

Data Index: 1436419 (Python Code)

Max Activating Token Index: 539

Text #11

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.5508. Min Act: -0.0000

Data Index: 1474911 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.4671. Min Act: -0.0000

Data Index: 1379135 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.5353. Min Act: -0.0000

Data Index: 1603351 (Python Code)

Max Activating Token Index: 99

Text #14

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.5070. Min Act: -0.0000

Data Index: 1653814 (Python Code)

Max Activating Token Index: 621

Text #15

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1581526 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.4990. Min Act: -0.0000

Data Index: 1529387 (Python Code)

Max Activating Token Index: 894

Text #17

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.3339. Min Act: -0.0000

Data Index: 1498931 (Python Code)

Max Activating Token Index: 748

Text #18

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1459213 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 2.0928. Min Range: -2.0928

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1530697 (Python Code)

Max Activating Token Index: 530