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

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

Neuron 142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2711. Min Act: -0.0000

Data Index: 935616 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1061145 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2369. Min Act: -0.0000

Data Index: 961715 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2346. Min Act: -0.0000

Data Index: 889570 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2253. Min Act: -0.0000

Data Index: 316240 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1633210 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2200. Min Act: -0.0000

Data Index: 972837 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2120. Min Act: -0.0000

Data Index: 542332 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1533978 (Python Code)

Max Activating Token Index: 663

Text #9

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1040185 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1051709 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1582287 (Python Code)

Max Activating Token Index: 340

Text #12

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1186773 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1052697 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1597405 (Python Code)

Max Activating Token Index: 1018

Text #15

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2034. Min Act: -0.0000

Data Index: 600438 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1312422 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1534110 (Python Code)

Max Activating Token Index: 996

Text #18

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1884. Min Act: -0.0000

Data Index: 283862 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2080. Min Act: -0.0000

Data Index: 153804 (C4 (Web Text))

Max Activating Token Index: 293