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

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

Neuron 585 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: 1.4092. Min Range: -1.4092

Max Act: 1.3560. Min Act: -0.0000

Data Index: 1263711 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.4092. Min Act: -0.0000

Data Index: 220764 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.3758. Min Act: -0.0000

Data Index: 426099 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2574. Min Act: -0.0000

Data Index: 489472 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2471. Min Act: -0.0000

Data Index: 681936 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1877. Min Act: -0.0000

Data Index: 847631 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1983. Min Act: -0.0000

Data Index: 135794 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.2043. Min Act: -0.0000

Data Index: 872737 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0718. Min Act: -0.0000

Data Index: 251816 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1722. Min Act: -0.0000

Data Index: 334234 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1405075 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1390. Min Act: -0.0000

Data Index: 317537 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0956. Min Act: -0.0000

Data Index: 715508 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0867. Min Act: -0.0000

Data Index: 918538 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0496. Min Act: -0.0000

Data Index: 55180 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0819. Min Act: -0.0000

Data Index: 102108 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.1093. Min Act: -0.0000

Data Index: 704715 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0337. Min Act: -0.0000

Data Index: 309504 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1294850 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 1.4092. Min Range: -1.4092

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1037970 (C4 (Web Text))

Max Activating Token Index: 543