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

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

Neuron 3768 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1434902 (Python Code)

Max Activating Token Index: 101

Text #1

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1540391 (Python Code)

Max Activating Token Index: 481

Text #2

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1581003 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1542989 (Python Code)

Max Activating Token Index: 552

Text #4

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1407322 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1419850 (Python Code)

Max Activating Token Index: 506

Text #6

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1603655 (Python Code)

Max Activating Token Index: 641

Text #7

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0912. Min Act: -0.0002

Data Index: 1389140 (Python Code)

Max Activating Token Index: 826

Text #8

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1637397 (Python Code)

Max Activating Token Index: 204

Text #9

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1498093 (Python Code)

Max Activating Token Index: 803

Text #10

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1554302 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1632391 (Python Code)

Max Activating Token Index: 436

Text #12

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1386025 (Python Code)

Max Activating Token Index: 368

Text #13

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1653626 (Python Code)

Max Activating Token Index: 715

Text #14

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1368310 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1360687 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1654043 (Python Code)

Max Activating Token Index: 433

Text #17

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1511439 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1550173 (Python Code)

Max Activating Token Index: 255

Text #19

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1539476 (Python Code)

Max Activating Token Index: 289