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

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

Neuron 1727 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1250963 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1182922 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1079525 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1118450 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6973. Min Act: -0.0000

Data Index: 873694 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6584. Min Act: -0.0000

Data Index: 566606 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6672. Min Act: -0.0000

Data Index: 131628 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6422. Min Act: -0.0000

Data Index: 396435 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6201. Min Act: -0.0000

Data Index: 663382 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1009983 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6930. Min Act: -0.0000

Data Index: 917410 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6298. Min Act: -0.0000

Data Index: 60594 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1330209 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6012. Min Act: -0.0000

Data Index: 655847 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6366. Min Act: -0.0000

Data Index: 578757 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1140198 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6738. Min Act: -0.0000

Data Index: 134045 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6571. Min Act: -0.0000

Data Index: 688854 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6270. Min Act: -0.0000

Data Index: 440797 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.7784. Min Range: -0.7784

Max Act: 0.6661. Min Act: -0.0000

Data Index: 699078 (C4 (Web Text))

Max Activating Token Index: 290