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

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

Neuron 3657 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: 5.2535. Min Range: -5.2535

Max Act: 5.2535. Min Act: -0.0001

Data Index: 443943 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.7303. Min Act: -0.0001

Data Index: 1277062 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.5704. Min Act: -0.0001

Data Index: 1290508 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.6837. Min Act: -0.0001

Data Index: 627113 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.5420. Min Act: -0.0001

Data Index: 567665 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.4776. Min Act: -0.0001

Data Index: 335719 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.3822. Min Act: -0.0001

Data Index: 1226753 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.2877. Min Act: -0.0001

Data Index: 886241 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.0852. Min Act: -0.0001

Data Index: 1164472 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.2352. Min Act: -0.0001

Data Index: 708154 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.1963. Min Act: -0.0001

Data Index: 1137609 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 5.2535. Min Range: -5.2535

Max Act: 4.1911. Min Act: -0.0001

Data Index: 649273 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 5.2535. Min Range: -5.2535

Max Act: 3.9656. Min Act: -0.0001

Data Index: 127825 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 5.2535. Min Range: -5.2535

Max Act: 3.6324. Min Act: -0.0001

Data Index: 474735 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 5.2535. Min Range: -5.2535

Max Act: 3.9151. Min Act: -0.0001

Data Index: 1193253 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 5.2535. Min Range: -5.2535

Max Act: 3.4405. Min Act: -0.0001

Data Index: 117579 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 5.2535. Min Range: -5.2535

Max Act: 3.8500. Min Act: -0.0001

Data Index: 688975 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 5.2535. Min Range: -5.2535

Max Act: 3.8589. Min Act: -0.0001

Data Index: 770835 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 5.2535. Min Range: -5.2535

Max Act: 3.8401. Min Act: -0.0001

Data Index: 1202321 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 5.2535. Min Range: -5.2535

Max Act: 3.8224. Min Act: -0.0001

Data Index: 88552 (C4 (Web Text))

Max Activating Token Index: 136