Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2956 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2713. Min Act: -0.0001

Data Index: 1356066 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2115. Min Act: -0.0001

Data Index: 552617 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2235. Min Act: -0.0001

Data Index: 1133119 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2035. Min Act: -0.0001

Data Index: 343325 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2086. Min Act: -0.0001

Data Index: 685898 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1937. Min Act: -0.0001

Data Index: 707803 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1090 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1992. Min Act: -0.0001

Data Index: 352316 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2041. Min Act: -0.0001

Data Index: 8684 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1877. Min Act: -0.0001

Data Index: 458085 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2048. Min Act: -0.0001

Data Index: 206927 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1214729 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2041. Min Act: -0.0001

Data Index: 167998 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2197. Min Act: -0.0001

Data Index: 317810 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1038604 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1840. Min Act: -0.0001

Data Index: 759712 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.2171. Min Act: -0.0001

Data Index: 856551 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1930. Min Act: -0.0001

Data Index: 697314 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1847. Min Act: -0.0001

Data Index: 832513 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.2713. Min Range: -0.2713

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1354274 (C4 (Web Text))

Max Activating Token Index: 546