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

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

Neuron 3723 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1181914 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.6378. Min Act: -0.0000

Data Index: 797383 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5654. Min Act: -0.0000

Data Index: 479767 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1185044 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5305. Min Act: -0.0000

Data Index: 917973 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1003115 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5326. Min Act: -0.0000

Data Index: 198530 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1099162 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1279417 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1260761 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5093. Min Act: -0.0000

Data Index: 450751 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5447. Min Act: -0.0000

Data Index: 858392 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5071. Min Act: -0.0000

Data Index: 381762 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1016603 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4985. Min Act: -0.0000

Data Index: 870040 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1112009 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1308792 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4676. Min Act: -0.0000

Data Index: 585629 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1010606 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4724. Min Act: -0.0000

Data Index: 317187 (C4 (Web Text))

Max Activating Token Index: 557