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

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

Neuron 1988 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.3637. Min Act: -0.0000

Data Index: 348919 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.3540. Min Act: -0.0000

Data Index: 497087 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.4105. Min Act: -0.0000

Data Index: 72104 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.1561. Min Act: -0.0000

Data Index: 122517 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.3624. Min Act: -0.0000

Data Index: 128674 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.3653. Min Act: -0.0000

Data Index: 643800 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.1015. Min Act: -0.0000

Data Index: 665890 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.2069. Min Act: -0.0000

Data Index: 578105 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.2391. Min Act: -0.0000

Data Index: 1517830 (Python Code)

Max Activating Token Index: 224

Text #9

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.1758. Min Act: -0.0000

Data Index: 144380 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.0622. Min Act: -0.0000

Data Index: 90538 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.0127. Min Act: -0.0000

Data Index: 1165534 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.1237. Min Act: -0.0000

Data Index: 1207050 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.1146. Min Act: -0.0000

Data Index: 1003393 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.0983. Min Act: -0.0000

Data Index: 1027060 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1225370 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.0640. Min Act: -0.0000

Data Index: 787498 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.0692. Min Act: -0.0000

Data Index: 315137 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 2.4105. Min Range: -2.4105

Max Act: 2.1941. Min Act: -0.0000

Data Index: 963836 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 2.4105. Min Range: -2.4105

Max Act: 1.9399. Min Act: -0.0000

Data Index: 307671 (C4 (Web Text))

Max Activating Token Index: 742