Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1574 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0002

Data Index: 850329 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0619. Min Act: -0.0002

Data Index: 593223 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0582. Min Act: -0.0002

Data Index: 63934 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0562. Min Act: -0.0002

Data Index: 103561 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1289912 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1237277 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0540. Min Act: -0.0002

Data Index: 836529 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0523. Min Act: -0.0002

Data Index: 881530 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0506. Min Act: -0.0002

Data Index: 73895 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0534. Min Act: -0.0001

Data Index: 560606 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0530. Min Act: -0.0002

Data Index: 963746 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0532. Min Act: -0.0002

Data Index: 905578 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0519. Min Act: -0.0002

Data Index: 432448 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0514. Min Act: -0.0002

Data Index: 698822 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1270474 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0496. Min Act: -0.0002

Data Index: 425814 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0503. Min Act: -0.0002

Data Index: 927398 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0492. Min Act: -0.0002

Data Index: 666712 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0493. Min Act: -0.0002

Data Index: 483473 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1346394 (C4 (Web Text))

Max Activating Token Index: 589