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

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

Neuron 4803 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0289. Min Range: -1.0289

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1172009 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.8619. Min Act: -0.0000

Data Index: 266080 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1388930 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7596. Min Act: -0.0000

Data Index: 504401 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7783. Min Act: -0.0001

Data Index: 304305 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.8101. Min Act: -0.0001

Data Index: 453994 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7256. Min Act: -0.0000

Data Index: 969669 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7540. Min Act: -0.0000

Data Index: 464035 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7837. Min Act: -0.0000

Data Index: 498798 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1408828 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7243. Min Act: -0.0000

Data Index: 294956 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1261963 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.6885. Min Act: -0.0000

Data Index: 886676 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.7093. Min Act: -0.0000

Data Index: 995808 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.6558. Min Act: -0.0001

Data Index: 1122702 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.6916. Min Act: -0.0000

Data Index: 302403 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.6254. Min Act: -0.0001

Data Index: 60854 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.6431. Min Act: -0.0000

Data Index: 485783 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.6058. Min Act: -0.0000

Data Index: 93814 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.0289. Min Range: -1.0289

Max Act: 0.6745. Min Act: -0.0000

Data Index: 908999 (C4 (Web Text))

Max Activating Token Index: 445