Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 896 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2256. Min Range: -1.2256

Max Act: 1.2256. Min Act: -0.0000

Data Index: 110903 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8649. Min Act: -0.0000

Data Index: 198261 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8481. Min Act: -0.0001

Data Index: 63271 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8147. Min Act: -0.0000

Data Index: 125772 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1125381 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.7773. Min Act: -0.0000

Data Index: 647177 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.7911. Min Act: -0.0001

Data Index: 512654 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.7836. Min Act: -0.0000

Data Index: 681827 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1342362 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1053318 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.7644. Min Act: -0.0001

Data Index: 821534 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1028040 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6580. Min Act: -0.0000

Data Index: 281047 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6519. Min Act: -0.0001

Data Index: 148352 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1080465 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6442. Min Act: -0.0001

Data Index: 1263063 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6603. Min Act: -0.0000

Data Index: 75063 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1123321 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6558. Min Act: -0.0001

Data Index: 1035158 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.6442. Min Act: -0.0000

Data Index: 469602 (C4 (Web Text))

Max Activating Token Index: 212