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

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

Neuron 5640 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: 2.7891. Min Range: -2.7891

Max Act: 2.4189. Min Act: -0.0000

Data Index: 343027 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 2.7891. Min Range: -2.7891

Max Act: 2.7891. Min Act: -0.0000

Data Index: 1186655 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 2.7891. Min Range: -2.7891

Max Act: 2.3696. Min Act: -0.0000

Data Index: 1426597 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 2.7891. Min Range: -2.7891

Max Act: 2.1856. Min Act: -0.0000

Data Index: 1641467 (Python Code)

Max Activating Token Index: 66

Text #4

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.7168. Min Act: -0.0000

Data Index: 642930 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 2.7891. Min Range: -2.7891

Max Act: 2.2251. Min Act: -0.0000

Data Index: 1410605 (Python Code)

Max Activating Token Index: 203

Text #6

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.7896. Min Act: -0.0000

Data Index: 1400717 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 2.7891. Min Range: -2.7891

Max Act: 2.0792. Min Act: -0.0000

Data Index: 1534754 (Python Code)

Max Activating Token Index: 558

Text #8

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.8776. Min Act: -0.0000

Data Index: 1606360 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.9827. Min Act: -0.0000

Data Index: 1444053 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1439004 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.8349. Min Act: -0.0000

Data Index: 1618514 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.8197. Min Act: -0.0000

Data Index: 561871 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.9186. Min Act: -0.0000

Data Index: 1365626 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.8882. Min Act: -0.0000

Data Index: 1411815 (Python Code)

Max Activating Token Index: 709

Text #15

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.9820. Min Act: -0.0000

Data Index: 1642970 (Python Code)

Max Activating Token Index: 497

Text #16

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.7897. Min Act: -0.0000

Data Index: 71254 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.9855. Min Act: -0.0000

Data Index: 1398895 (Python Code)

Max Activating Token Index: 621

Text #18

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.9510. Min Act: -0.0000

Data Index: 1586927 (Python Code)

Max Activating Token Index: 865

Text #19

Max Range: 2.7891. Min Range: -2.7891

Max Act: 1.8626. Min Act: -0.0000

Data Index: 1431643 (Python Code)

Max Activating Token Index: 574