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

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

Neuron 5676 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1519029 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1369963 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2544. Min Act: -0.0001

Data Index: 1197797 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1050801 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2039. Min Act: -0.0000

Data Index: 804855 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2244. Min Act: -0.0000

Data Index: 256972 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2137. Min Act: -0.0000

Data Index: 779143 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2148. Min Act: -0.0001

Data Index: 355905 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2127. Min Act: -0.0001

Data Index: 682355 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2104. Min Act: -0.0000

Data Index: 643777 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2187. Min Act: -0.0000

Data Index: 590366 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2113. Min Act: -0.0000

Data Index: 837858 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2033. Min Act: -0.0001

Data Index: 688258 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2120. Min Act: -0.0000

Data Index: 828600 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2019. Min Act: -0.0000

Data Index: 967214 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2046. Min Act: -0.0001

Data Index: 312537 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2058. Min Act: -0.0001

Data Index: 971512 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1005376 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2060. Min Act: -0.0000

Data Index: 672272 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2042. Min Act: -0.0000

Data Index: 889991 (C4 (Web Text))

Max Activating Token Index: 342