Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1225 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6228. Min Act: -0.0000

Data Index: 854445 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6921. Min Act: -0.0000

Data Index: 351985 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6429. Min Act: -0.0000

Data Index: 770945 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1055417 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5904. Min Act: -0.0000

Data Index: 51973 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5791. Min Act: -0.0000

Data Index: 989658 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1315940 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5778. Min Act: -0.0000

Data Index: 997459 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1124829 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5565. Min Act: -0.0000

Data Index: 514639 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5417. Min Act: -0.0000

Data Index: 857428 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1307830 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5304. Min Act: -0.0000

Data Index: 431300 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5052. Min Act: -0.0000

Data Index: 973054 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4915. Min Act: -0.0000

Data Index: 427917 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5057. Min Act: -0.0000

Data Index: 901012 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5042. Min Act: -0.0000

Data Index: 275657 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1165699 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4901. Min Act: -0.0000

Data Index: 962172 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1140471 (C4 (Web Text))

Max Activating Token Index: 734