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

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

Neuron 2598 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: 1.3133. Min Range: -1.3133

Max Act: 1.3133. Min Act: -0.0000

Data Index: 646917 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1021627 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.0718. Min Act: -0.0000

Data Index: 48436 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.1110. Min Act: -0.0000

Data Index: 226235 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.0730. Min Act: -0.0000

Data Index: 368138 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9684. Min Act: -0.0000

Data Index: 706463 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1244561 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.3133. Min Range: -1.3133

Max Act: 1.0344. Min Act: -0.0000

Data Index: 140354 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9986. Min Act: -0.0000

Data Index: 155404 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9832. Min Act: -0.0000

Data Index: 386807 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9724. Min Act: -0.0000

Data Index: 910578 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9462. Min Act: -0.0000

Data Index: 644037 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9384. Min Act: -0.0000

Data Index: 337720 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9469. Min Act: -0.0000

Data Index: 452606 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9076. Min Act: -0.0000

Data Index: 103284 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1034938 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1566934 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9139. Min Act: -0.0000

Data Index: 467075 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1461671 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 1.3133. Min Range: -1.3133

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1547512 (Python Code)

Max Activating Token Index: 385