Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 217 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0004

Data Index: 745608 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0703. Min Act: -0.0004

Data Index: 542779 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0593. Min Act: -0.0004

Data Index: 63662 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0559. Min Act: -0.0004

Data Index: 822995 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0650. Min Act: -0.0004

Data Index: 47074 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0641. Min Act: -0.0004

Data Index: 975098 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0578. Min Act: -0.0004

Data Index: 1240292 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0515. Min Act: -0.0004

Data Index: 877417 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0625. Min Act: -0.0004

Data Index: 268922 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0599. Min Act: -0.0004

Data Index: 1609587 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0547. Min Act: -0.0004

Data Index: 841569 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0587. Min Act: -0.0004

Data Index: 1580681 (Python Code)

Max Activating Token Index: 438

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0560. Min Act: -0.0004

Data Index: 1145121 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0559. Min Act: -0.0004

Data Index: 794255 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0578. Min Act: -0.0004

Data Index: 917492 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0628. Min Act: -0.0004

Data Index: 629496 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0578. Min Act: -0.0004

Data Index: 1259454 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0555. Min Act: -0.0004

Data Index: 1331611 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0573. Min Act: -0.0004

Data Index: 789729 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0593. Min Act: -0.0004

Data Index: 278849 (C4 (Web Text))

Max Activating Token Index: 459