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

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

Neuron 3497 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.3744. Min Act: -0.0001

Data Index: 1208604 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.1479. Min Act: -0.0000

Data Index: 1230505 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.3890. Min Act: -0.0001

Data Index: 606130 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.1516. Min Act: -0.0000

Data Index: 716882 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.0356. Min Act: -0.0000

Data Index: 527617 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.9240. Min Act: -0.0000

Data Index: 414451 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.0690. Min Act: -0.0000

Data Index: 1087533 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.0743. Min Act: -0.0000

Data Index: 338236 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.8470. Min Act: -0.0000

Data Index: 779570 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.4013. Min Act: -0.0000

Data Index: 354977 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.1740. Min Act: -0.0000

Data Index: 789657 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 2.4013. Min Range: -2.4013

Max Act: 2.1314. Min Act: -0.0000

Data Index: 714385 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.9008. Min Act: -0.0000

Data Index: 433391 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.8982. Min Act: -0.0001

Data Index: 690763 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.8580. Min Act: -0.0000

Data Index: 1153755 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.9891. Min Act: -0.0000

Data Index: 945417 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.9796. Min Act: -0.0000

Data Index: 264408 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.9639. Min Act: -0.0000

Data Index: 186485 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.8058. Min Act: -0.0000

Data Index: 548391 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 2.4013. Min Range: -2.4013

Max Act: 1.8255. Min Act: -0.0000

Data Index: 1266538 (C4 (Web Text))

Max Activating Token Index: 566