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

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

Neuron 102 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: 0.6958. Min Range: -0.6958

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1365700 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1443162 (Python Code)

Max Activating Token Index: 345

Text #2

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1456951 (Python Code)

Max Activating Token Index: 324

Text #3

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6614. Min Act: -0.0001

Data Index: 1464655 (Python Code)

Max Activating Token Index: 553

Text #4

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6088. Min Act: -0.0001

Data Index: 1382377 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1544382 (Python Code)

Max Activating Token Index: 641

Text #6

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1374190 (Python Code)

Max Activating Token Index: 655

Text #7

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1378747 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5896. Min Act: -0.0001

Data Index: 1556035 (Python Code)

Max Activating Token Index: 467

Text #9

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1530373 (Python Code)

Max Activating Token Index: 575

Text #10

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1490120 (Python Code)

Max Activating Token Index: 860

Text #11

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1564237 (Python Code)

Max Activating Token Index: 1012

Text #12

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5887. Min Act: -0.0001

Data Index: 1397548 (Python Code)

Max Activating Token Index: 326

Text #13

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1604289 (Python Code)

Max Activating Token Index: 963

Text #14

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5685. Min Act: -0.0001

Data Index: 1630464 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1606461 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1409787 (Python Code)

Max Activating Token Index: 912

Text #17

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1409588 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6346. Min Act: -0.0001

Data Index: 1632714 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1578056 (Python Code)

Max Activating Token Index: 289