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

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

Neuron 3943 in Layer 1

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: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0002

Data Index: 328214 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0834. Min Act: -0.0002

Data Index: 359478 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0829. Min Act: -0.0002

Data Index: 406512 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0801. Min Act: -0.0002

Data Index: 394521 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0798. Min Act: -0.0002

Data Index: 21084 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0763. Min Act: -0.0002

Data Index: 797174 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1298929 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0784. Min Act: -0.0002

Data Index: 51987 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0771. Min Act: -0.0002

Data Index: 560357 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1052298 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0770. Min Act: -0.0002

Data Index: 25095 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1238468 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0751. Min Act: -0.0002

Data Index: 309741 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0755. Min Act: -0.0002

Data Index: 985258 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1019225 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1326437 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1151845 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0739. Min Act: -0.0002

Data Index: 198989 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1104561 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0735. Min Act: -0.0002

Data Index: 293093 (C4 (Web Text))

Max Activating Token Index: 916