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

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

Neuron 3470 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2478. Min Range: -4.2478

Max Act: 4.0519. Min Act: -0.0000

Data Index: 1642463 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 4.2478. Min Range: -4.2478

Max Act: 4.0639. Min Act: -0.0000

Data Index: 1643947 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 4.2478. Min Range: -4.2478

Max Act: 4.0418. Min Act: -0.0000

Data Index: 1575160 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 4.2478. Min Range: -4.2478

Max Act: 4.0134. Min Act: -0.0000

Data Index: 1524844 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.9729. Min Act: -0.0000

Data Index: 1493919 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 4.2478. Min Range: -4.2478

Max Act: 4.2478. Min Act: -0.0000

Data Index: 1456581 (Python Code)

Max Activating Token Index: 875

Text #6

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8309. Min Act: -0.0000

Data Index: 1494802 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8791. Min Act: -0.0000

Data Index: 1610273 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8608. Min Act: -0.0000

Data Index: 1495705 (Python Code)

Max Activating Token Index: 531

Text #9

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.8292. Min Act: -0.0000

Data Index: 1623226 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.7713. Min Act: -0.0000

Data Index: 1417768 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.7195. Min Act: -0.0000

Data Index: 1485270 (Python Code)

Max Activating Token Index: 547

Text #12

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.7008. Min Act: -0.0000

Data Index: 1360583 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.5266. Min Act: -0.0000

Data Index: 1506171 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.6678. Min Act: -0.0000

Data Index: 1596553 (Python Code)

Max Activating Token Index: 687

Text #15

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.6328. Min Act: -0.0000

Data Index: 1361486 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.6304. Min Act: -0.0000

Data Index: 1400615 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.7595. Min Act: -0.0000

Data Index: 1429436 (Python Code)

Max Activating Token Index: 708

Text #18

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.5858. Min Act: -0.0000

Data Index: 1578747 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 4.2478. Min Range: -4.2478

Max Act: 3.5685. Min Act: -0.0000

Data Index: 1609017 (Python Code)

Max Activating Token Index: 410