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

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

Neuron 5073 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8325. Min Act: -0.0001

Data Index: 393860 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8033. Min Act: -0.0001

Data Index: 293037 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7307. Min Act: -0.0001

Data Index: 667228 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7206. Min Act: -0.0001

Data Index: 34195 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6964. Min Act: -0.0001

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7129. Min Act: -0.0001

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6809. Min Act: -0.0001

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7009. Min Act: -0.0001

Data Index: 273030 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7189. Min Act: -0.0001

Data Index: 123075 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6755. Min Act: -0.0001

Data Index: 300081 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6994. Min Act: -0.0001

Data Index: 433777 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6898. Min Act: -0.0001

Data Index: 956824 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.7132. Min Act: -0.0000

Data Index: 565567 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6632. Min Act: -0.0001

Data Index: 1051722 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6672. Min Act: -0.0001

Data Index: 511639 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6998. Min Act: -0.0001

Data Index: 947581 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6802. Min Act: -0.0001

Data Index: 303462 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6173. Min Act: -0.0001

Data Index: 151439 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6341. Min Act: -0.0000

Data Index: 21026 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6904. Min Act: -0.0001

Data Index: 416244 (C4 (Web Text))

Max Activating Token Index: 985