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

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

Neuron 2872 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6831. Min Act: -0.0001

Data Index: 451823 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6609. Min Act: -0.0001

Data Index: 1226044 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6569. Min Act: -0.0001

Data Index: 452885 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6312. Min Act: -0.0001

Data Index: 677382 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6181. Min Act: -0.0001

Data Index: 1225610 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6311. Min Act: -0.0001

Data Index: 792156 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6159. Min Act: -0.0001

Data Index: 2314 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6211. Min Act: -0.0001

Data Index: 865937 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6176. Min Act: -0.0001

Data Index: 624647 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6168. Min Act: -0.0001

Data Index: 207178 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6205. Min Act: -0.0001

Data Index: 941693 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6231. Min Act: -0.0001

Data Index: 916192 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6161. Min Act: -0.0001

Data Index: 417480 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6159. Min Act: -0.0001

Data Index: 998041 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6071. Min Act: -0.0001

Data Index: 937910 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5973. Min Act: -0.0001

Data Index: 824632 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6018. Min Act: -0.0001

Data Index: 712144 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6010. Min Act: -0.0001

Data Index: 1034086 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6032. Min Act: -0.0001

Data Index: 143492 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6134. Min Act: -0.0001

Data Index: 161882 (C4 (Web Text))

Max Activating Token Index: 28