Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2653 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7989. Min Act: -0.0001

Data Index: 141264 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7517. Min Act: -0.0001

Data Index: 519479 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7327. Min Act: -0.0001

Data Index: 424848 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7565. Min Act: -0.0001

Data Index: 840521 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7315. Min Act: -0.0001

Data Index: 952250 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6987. Min Act: -0.0001

Data Index: 52028 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7528. Min Act: -0.0001

Data Index: 1122860 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7077. Min Act: -0.0001

Data Index: 15777 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6658. Min Act: -0.0001

Data Index: 245724 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6576. Min Act: -0.0001

Data Index: 254542 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6799. Min Act: -0.0001

Data Index: 343791 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6826. Min Act: -0.0001

Data Index: 808726 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.7011. Min Act: -0.0001

Data Index: 1272425 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6848. Min Act: -0.0001

Data Index: 147949 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6270. Min Act: -0.0001

Data Index: 700419 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6747. Min Act: -0.0001

Data Index: 278327 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6752. Min Act: -0.0001

Data Index: 215391 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6496. Min Act: -0.0001

Data Index: 165904 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6453. Min Act: -0.0001

Data Index: 648049 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.7989. Min Range: -0.7989

Max Act: 0.6292. Min Act: -0.0001

Data Index: 344618 (C4 (Web Text))

Max Activating Token Index: 743