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

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

Neuron 712 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2589. Min Act: -0.0002

Data Index: 443895 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2302. Min Act: -0.0002

Data Index: 189357 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2332. Min Act: -0.0002

Data Index: 926950 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2198. Min Act: -0.0002

Data Index: 993264 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2238. Min Act: -0.0002

Data Index: 895358 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2381. Min Act: -0.0002

Data Index: 43590 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2274. Min Act: -0.0001

Data Index: 641230 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2113. Min Act: -0.0002

Data Index: 528525 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2020. Min Act: -0.0002

Data Index: 255396 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2059. Min Act: -0.0001

Data Index: 96979 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2126. Min Act: -0.0001

Data Index: 479681 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2060. Min Act: -0.0001

Data Index: 766001 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2134. Min Act: -0.0002

Data Index: 432485 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2020. Min Act: -0.0002

Data Index: 815524 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1937. Min Act: -0.0001

Data Index: 316904 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1879. Min Act: -0.0001

Data Index: 381989 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1992. Min Act: -0.0001

Data Index: 480739 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1952. Min Act: -0.0002

Data Index: 1117475 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1894. Min Act: -0.0001

Data Index: 650022 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1107187 (C4 (Web Text))

Max Activating Token Index: 66