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

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

Neuron 3784 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1320. Min Act: -0.0003

Data Index: 446100 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1145. Min Act: -0.0003

Data Index: 1103990 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1076. Min Act: -0.0003

Data Index: 1016950 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1038. Min Act: -0.0003

Data Index: 257175 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1039. Min Act: -0.0003

Data Index: 364628 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1038. Min Act: -0.0003

Data Index: 220384 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1030. Min Act: -0.0003

Data Index: 1070226 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1030. Min Act: -0.0003

Data Index: 553865 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1013. Min Act: -0.0003

Data Index: 1315522 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0995. Min Act: -0.0003

Data Index: 21245 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0991. Min Act: -0.0003

Data Index: 754078 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0987. Min Act: -0.0003

Data Index: 1317789 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0980. Min Act: -0.0003

Data Index: 555508 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0966. Min Act: -0.0003

Data Index: 353851 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0963. Min Act: -0.0003

Data Index: 235354 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0948. Min Act: -0.0003

Data Index: 1283750 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0943. Min Act: -0.0003

Data Index: 1174596 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0940. Min Act: -0.0003

Data Index: 798740 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1112950 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.0937. Min Act: -0.0003

Data Index: 90927 (C4 (Web Text))

Max Activating Token Index: 15