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

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

Neuron 3129 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.9072. Min Act: -0.0002

Data Index: 1595858 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8769. Min Act: -0.0002

Data Index: 1602698 (Python Code)

Max Activating Token Index: 845

Text #2

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8799. Min Act: -0.0002

Data Index: 1514771 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8422. Min Act: -0.0002

Data Index: 1533649 (Python Code)

Max Activating Token Index: 93

Text #4

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8573. Min Act: -0.0002

Data Index: 1594332 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8073. Min Act: -0.0002

Data Index: 1019213 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8470. Min Act: -0.0002

Data Index: 1463148 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8397. Min Act: -0.0002

Data Index: 1394009 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8219. Min Act: -0.0002

Data Index: 471850 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7843. Min Act: -0.0002

Data Index: 1569924 (Python Code)

Max Activating Token Index: 875

Text #10

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7857. Min Act: -0.0002

Data Index: 1146419 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7918. Min Act: -0.0002

Data Index: 670918 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7721. Min Act: -0.0002

Data Index: 1518177 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7890. Min Act: -0.0002

Data Index: 1595472 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7545. Min Act: -0.0002

Data Index: 665559 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7346. Min Act: -0.0002

Data Index: 1603887 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7600. Min Act: -0.0002

Data Index: 1580813 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7425. Min Act: -0.0002

Data Index: 255976 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7335. Min Act: -0.0002

Data Index: 110623 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7080. Min Act: -0.0002

Data Index: 1546424 (Python Code)

Max Activating Token Index: 673