Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 647 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1298358 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1049308 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1193054 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0922. Min Act: -0.0000

Data Index: 653280 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0750. Min Act: -0.0000

Data Index: 944627 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0698. Min Act: 0.0000

Data Index: 231638 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0616. Min Act: -0.0000

Data Index: 788328 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0653. Min Act: -0.0000

Data Index: 722203 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0668. Min Act: -0.0000

Data Index: 389902 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0641. Min Act: -0.0000

Data Index: 949512 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0604. Min Act: -0.0000

Data Index: 361578 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0595. Min Act: -0.0000

Data Index: 403481 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0907. Min Act: -0.0000

Data Index: 742160 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0626. Min Act: -0.0000

Data Index: 656463 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0578. Min Act: -0.0000

Data Index: 678542 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0570. Min Act: -0.0000

Data Index: 109794 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0541. Min Act: -0.0000

Data Index: 270989 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0521. Min Act: -0.0000

Data Index: 32872 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0595. Min Act: -0.0000

Data Index: 1192889 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.2146. Min Range: -0.2146

Max Act: 0.0539. Min Act: -0.0000

Data Index: 274095 (C4 (Web Text))

Max Activating Token Index: 972