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

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

Neuron 5008 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.4799. Min Act: -0.0001

Data Index: 568306 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.6102. Min Act: -0.0001

Data Index: 1317476 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.5508. Min Act: -0.0001

Data Index: 1265425 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.6019. Min Act: -0.0001

Data Index: 1329064 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.3382. Min Act: -0.0001

Data Index: 602420 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.5636. Min Act: -0.0001

Data Index: 229268 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.5652. Min Act: -0.0001

Data Index: 480771 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.4751. Min Act: -0.0001

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.5712. Min Act: -0.0001

Data Index: 1128529 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.3993. Min Act: -0.0001

Data Index: 128473 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.5361. Min Act: -0.0001

Data Index: 596975 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2667. Min Act: -0.0001

Data Index: 757675 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.3751. Min Act: -0.0001

Data Index: 681674 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2335. Min Act: -0.0001

Data Index: 1041868 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.3754. Min Act: -0.0001

Data Index: 65184 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2477. Min Act: -0.0001

Data Index: 1322442 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2246. Min Act: -0.0001

Data Index: 678287 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2597. Min Act: -0.0001

Data Index: 1124852 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.3746. Min Act: -0.0001

Data Index: 1344012 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 1.6102. Min Range: -1.6102

Max Act: 1.2375. Min Act: -0.0001

Data Index: 43229 (C4 (Web Text))

Max Activating Token Index: 1005