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

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

Neuron 3730 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1252. Min Act: -0.0002

Data Index: 851938 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1137. Min Act: -0.0002

Data Index: 588673 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1002. Min Act: -0.0002

Data Index: 815155 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1241973 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0908. Min Act: -0.0002

Data Index: 239269 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0999. Min Act: -0.0002

Data Index: 538022 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0952. Min Act: -0.0002

Data Index: 136729 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0975. Min Act: -0.0002

Data Index: 618685 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1072177 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0925. Min Act: -0.0002

Data Index: 451066 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0952. Min Act: -0.0002

Data Index: 546682 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1208013 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0946. Min Act: -0.0002

Data Index: 248467 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0908. Min Act: -0.0002

Data Index: 612283 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0900. Min Act: -0.0002

Data Index: 913468 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0934. Min Act: -0.0002

Data Index: 514984 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0862. Min Act: -0.0002

Data Index: 315694 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0904. Min Act: -0.0002

Data Index: 115268 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0900. Min Act: -0.0002

Data Index: 777063 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0837. Min Act: -0.0002

Data Index: 631130 (C4 (Web Text))

Max Activating Token Index: 698