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

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

Neuron 4821 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: 0.1028. Min Range: -0.1028

Max Act: 0.1028. Min Act: -0.0001

Data Index: 567224 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1028. Min Act: -0.0001

Data Index: 769061 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0986. Min Act: -0.0001

Data Index: 590036 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1286503 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0940. Min Act: -0.0001

Data Index: 592441 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1479852 (Python Code)

Max Activating Token Index: 578

Text #6

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0848. Min Act: -0.0001

Data Index: 489624 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0901. Min Act: -0.0001

Data Index: 347101 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0875. Min Act: -0.0001

Data Index: 952427 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0920. Min Act: -0.0001

Data Index: 725619 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0840. Min Act: -0.0001

Data Index: 198973 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0810. Min Act: -0.0001

Data Index: 424264 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1220785 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0807. Min Act: -0.0001

Data Index: 282618 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0761. Min Act: -0.0001

Data Index: 948423 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0724. Min Act: -0.0001

Data Index: 622841 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1076967 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1329720 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0766. Min Act: -0.0001

Data Index: 257311 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0710. Min Act: -0.0001

Data Index: 481113 (C4 (Web Text))

Max Activating Token Index: 135