Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2012 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1063. Min Act: -0.0002

Data Index: 885897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0915. Min Act: -0.0002

Data Index: 537484 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1057. Min Act: -0.0002

Data Index: 334178 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1424653 (Python Code)

Max Activating Token Index: 409

Text #4

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1114389 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1603899 (Python Code)

Max Activating Token Index: 458

Text #6

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0912. Min Act: -0.0002

Data Index: 118013 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1386143 (Python Code)

Max Activating Token Index: 640

Text #8

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0891. Min Act: -0.0002

Data Index: 222955 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1001. Min Act: -0.0002

Data Index: 484297 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0950. Min Act: -0.0002

Data Index: 501188 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0905. Min Act: -0.0002

Data Index: 684939 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0907. Min Act: -0.0002

Data Index: 397219 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0830. Min Act: -0.0002

Data Index: 429165 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1631130 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1631136 (Python Code)

Max Activating Token Index: 381

Text #16

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0912. Min Act: -0.0002

Data Index: 873994 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1514546 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0860. Min Act: -0.0002

Data Index: 527737 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1441890 (Python Code)

Max Activating Token Index: 467