Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1289 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1456122 (Python Code)

Max Activating Token Index: 179

Text #1

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0056. Min Act: -0.0005

Data Index: 732461 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0057. Min Act: -0.0005

Data Index: 347930 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1030272 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1319464 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1312939 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1172773 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1147901 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 528798 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 356340 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 278923 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 269073 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0005

Data Index: 782669 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0006

Data Index: 361663 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0005

Data Index: 706946 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0005

Data Index: 814513 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0005

Data Index: 125507 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0005

Data Index: 545460 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0005

Data Index: 307150 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0006

Data Index: 138543 (C4 (Web Text))

Max Activating Token Index: 201