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

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

Neuron 603 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.5962. Min Act: -0.0001

Data Index: 1511976 (Python Code)

Max Activating Token Index: 177

Text #1

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4773. Min Act: -0.0001

Data Index: 1580379 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.5046. Min Act: -0.0001

Data Index: 1567058 (Python Code)

Max Activating Token Index: 428

Text #3

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4321. Min Act: -0.0001

Data Index: 1365454 (Python Code)

Max Activating Token Index: 291

Text #4

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4228. Min Act: -0.0001

Data Index: 1489330 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1576516 (Python Code)

Max Activating Token Index: 741

Text #6

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4324. Min Act: -0.0001

Data Index: 1465885 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4004. Min Act: -0.0001

Data Index: 1584050 (Python Code)

Max Activating Token Index: 781

Text #8

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4060. Min Act: -0.0001

Data Index: 1490491 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1566837 (Python Code)

Max Activating Token Index: 715

Text #10

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1638485 (Python Code)

Max Activating Token Index: 620

Text #11

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3790. Min Act: -0.0001

Data Index: 1446727 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4008. Min Act: -0.0001

Data Index: 1538488 (Python Code)

Max Activating Token Index: 276

Text #13

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1541572 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3286. Min Act: -0.0001

Data Index: 1627266 (Python Code)

Max Activating Token Index: 556

Text #15

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3554. Min Act: -0.0001

Data Index: 1420699 (Python Code)

Max Activating Token Index: 752

Text #16

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3534. Min Act: -0.0001

Data Index: 1413099 (Python Code)

Max Activating Token Index: 775

Text #17

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3282. Min Act: -0.0001

Data Index: 1451735 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3497. Min Act: -0.0001

Data Index: 1537619 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3506. Min Act: -0.0001

Data Index: 1515331 (Python Code)

Max Activating Token Index: 256