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

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

Neuron 2035 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: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0001

Data Index: 13644 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1049287 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1284568 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0988. Min Act: -0.0001

Data Index: 741804 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1143. Min Act: -0.0001

Data Index: 589188 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1010. Min Act: -0.0001

Data Index: 260588 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1007. Min Act: -0.0001

Data Index: 98176 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1338170 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1208731 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0983. Min Act: -0.0001

Data Index: 645379 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1001. Min Act: -0.0001

Data Index: 960720 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0988. Min Act: -0.0001

Data Index: 345249 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0924. Min Act: -0.0001

Data Index: 47918 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0971. Min Act: -0.0001

Data Index: 908138 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1274616 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0845. Min Act: -0.0001

Data Index: 871881 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0822. Min Act: -0.0001

Data Index: 829787 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0889. Min Act: -0.0001

Data Index: 750310 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0910. Min Act: -0.0001

Data Index: 140502 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0836. Min Act: -0.0001

Data Index: 557838 (C4 (Web Text))

Max Activating Token Index: 975