Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1873 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1294. Min Act: -0.0003

Data Index: 882896 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1197. Min Act: -0.0003

Data Index: 60050 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1084. Min Act: -0.0003

Data Index: 1300832 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1039. Min Act: -0.0003

Data Index: 1332770 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1049. Min Act: -0.0003

Data Index: 164898 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1017. Min Act: -0.0003

Data Index: 1267121 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0985. Min Act: -0.0002

Data Index: 40128 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0964. Min Act: -0.0003

Data Index: 755311 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0931. Min Act: -0.0004

Data Index: 1096529 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0909. Min Act: -0.0003

Data Index: 1290111 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0912. Min Act: -0.0004

Data Index: 420792 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0892. Min Act: -0.0003

Data Index: 649290 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0922. Min Act: -0.0001

Data Index: 466351 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1205181 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1132006 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1529354 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0893. Min Act: -0.0003

Data Index: 1281564 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0893. Min Act: -0.0003

Data Index: 370764 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0851. Min Act: -0.0003

Data Index: 133025 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0882. Min Act: -0.0003

Data Index: 1655390 (Python Code)

Max Activating Token Index: 744