Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2447 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0908. Min Act: -0.0001

Data Index: 920736 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0931. Min Act: -0.0001

Data Index: 561093 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1496319 (Python Code)

Max Activating Token Index: 444

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0001

Data Index: 934450 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0841. Min Act: -0.0001

Data Index: 162156 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1196898 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0751. Min Act: -0.0001

Data Index: 97892 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0773. Min Act: -0.0000

Data Index: 197167 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0577. Min Act: -0.0000

Data Index: 340655 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0718. Min Act: -0.0000

Data Index: 114844 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0613. Min Act: -0.0001

Data Index: 425427 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0655. Min Act: -0.0000

Data Index: 528528 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1059703 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0597. Min Act: -0.0000

Data Index: 242969 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1367496 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0609. Min Act: -0.0000

Data Index: 758913 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0578. Min Act: -0.0001

Data Index: 245364 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0552. Min Act: -0.0000

Data Index: 268974 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0566. Min Act: -0.0001

Data Index: 189750 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0561. Min Act: -0.0000

Data Index: 563250 (C4 (Web Text))

Max Activating Token Index: 299