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

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

Neuron 5988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1535. Min Act: -0.0002

Data Index: 1186454 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1202. Min Act: -0.0002

Data Index: 1148531 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1093. Min Act: -0.0002

Data Index: 117982 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1013. Min Act: -0.0002

Data Index: 358244 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1034. Min Act: -0.0002

Data Index: 695724 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1029. Min Act: -0.0002

Data Index: 9898 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0981. Min Act: -0.0002

Data Index: 638109 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1003. Min Act: -0.0002

Data Index: 876253 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1019387 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1316486 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0944. Min Act: -0.0002

Data Index: 129047 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0901. Min Act: -0.0002

Data Index: 254277 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0932. Min Act: -0.0002

Data Index: 333986 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0925. Min Act: -0.0002

Data Index: 846601 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0930. Min Act: -0.0002

Data Index: 331696 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1223435 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0876. Min Act: -0.0002

Data Index: 385459 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0878. Min Act: -0.0002

Data Index: 802282 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0855. Min Act: -0.0002

Data Index: 343961 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.0856. Min Act: -0.0002

Data Index: 436175 (C4 (Web Text))

Max Activating Token Index: 975