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

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

Neuron 1869 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1489174 (Python Code)

Max Activating Token Index: 432

Text #1

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1523182 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.4119. Min Act: -0.0000

Data Index: 994620 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.2453. Min Act: -0.0000

Data Index: 913904 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1572408 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.3691. Min Act: -0.0000

Data Index: 1629253 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1533250 (Python Code)

Max Activating Token Index: 1022

Text #7

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1436563 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.3895. Min Act: -0.0000

Data Index: 1536429 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1473484 (Python Code)

Max Activating Token Index: 773

Text #10

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1595424 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1401448 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.1060. Min Act: -0.0000

Data Index: 726806 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.3273. Min Act: -0.0000

Data Index: 1605622 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.2927. Min Act: -0.0000

Data Index: 69627 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.1586. Min Act: -0.0000

Data Index: 695543 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.2040. Min Act: -0.0000

Data Index: 434180 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.1211. Min Act: -0.0000

Data Index: 531162 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.2249. Min Act: -0.0000

Data Index: 36911 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.4674. Min Range: -1.4674

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1398368 (Python Code)

Max Activating Token Index: 305