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

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

Neuron 2746 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.2524. Min Act: -0.0000

Data Index: 340726 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.3598. Min Act: -0.0000

Data Index: 1313022 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.1610. Min Act: -0.0000

Data Index: 556501 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.2286. Min Act: -0.0000

Data Index: 665307 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.2104. Min Act: -0.0000

Data Index: 1152044 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 2.3598. Min Range: -2.3598

Max Act: 1.9225. Min Act: -0.0000

Data Index: 923403 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.1387. Min Act: -0.0000

Data Index: 448258 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.0206. Min Act: -0.0000

Data Index: 260869 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1592810 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.0055. Min Act: -0.0000

Data Index: 323900 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 2.3598. Min Range: -2.3598

Max Act: 1.8650. Min Act: -0.0000

Data Index: 1233333 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 2.3598. Min Range: -2.3598

Max Act: 1.9586. Min Act: 0.0000

Data Index: 1110489 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.0251. Min Act: -0.0000

Data Index: 558088 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 2.3598. Min Range: -2.3598

Max Act: 1.9105. Min Act: 0.0000

Data Index: 979484 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.0074. Min Act: -0.0000

Data Index: 1000400 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 2.3598. Min Range: -2.3598

Max Act: 1.9353. Min Act: 0.0000

Data Index: 270468 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 2.3598. Min Range: -2.3598

Max Act: 2.0113. Min Act: -0.0000

Data Index: 626991 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 2.3598. Min Range: -2.3598

Max Act: 1.8769. Min Act: -0.0000

Data Index: 1224175 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 2.3598. Min Range: -2.3598

Max Act: 1.8635. Min Act: -0.0000

Data Index: 1278851 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 2.3598. Min Range: -2.3598

Max Act: 1.8513. Min Act: -0.0000

Data Index: 1469628 (Python Code)

Max Activating Token Index: 597