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

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

Neuron 3190 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.1785. Min Act: -0.0001

Data Index: 670873 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 1.1785. Min Range: -1.1785

Max Act: 1.0474. Min Act: -0.0001

Data Index: 534484 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9432. Min Act: -0.0001

Data Index: 41981 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7817. Min Act: -0.0001

Data Index: 1343008 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.9012. Min Act: -0.0001

Data Index: 897060 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.8243. Min Act: -0.0001

Data Index: 1107553 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7338. Min Act: -0.0001

Data Index: 1341970 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1337979 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7569. Min Act: -0.0001

Data Index: 444717 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7600. Min Act: -0.0001

Data Index: 803890 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7124. Min Act: -0.0001

Data Index: 152578 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7088. Min Act: -0.0001

Data Index: 423103 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7466. Min Act: -0.0001

Data Index: 321981 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7267. Min Act: -0.0001

Data Index: 572558 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7000. Min Act: -0.0001

Data Index: 1347347 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.5996. Min Act: -0.0001

Data Index: 911777 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.6647. Min Act: -0.0001

Data Index: 888232 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.7249. Min Act: -0.0001

Data Index: 183284 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.6600. Min Act: -0.0001

Data Index: 617899 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.1785. Min Range: -1.1785

Max Act: 0.6472. Min Act: -0.0001

Data Index: 145486 (C4 (Web Text))

Max Activating Token Index: 597