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

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

Neuron 5795 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.5541. Min Act: -0.0000

Data Index: 1363381 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.4711. Min Act: -0.0000

Data Index: 1487604 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.5524. Min Act: -0.0000

Data Index: 1480018 (Python Code)

Max Activating Token Index: 1001

Text #3

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.3318. Min Act: -0.0000

Data Index: 1580606 (Python Code)

Max Activating Token Index: 880

Text #4

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.3009. Min Act: -0.0000

Data Index: 1407664 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.4668. Min Act: -0.0000

Data Index: 1445270 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.0707. Min Act: -0.0000

Data Index: 1615608 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.2278. Min Act: -0.0000

Data Index: 1475164 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.1586. Min Act: -0.0000

Data Index: 1376661 (Python Code)

Max Activating Token Index: 136

Text #9

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.1432. Min Act: -0.0000

Data Index: 1583715 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.1260. Min Act: -0.0000

Data Index: 1433337 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.0829. Min Act: -0.0000

Data Index: 1399643 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.0667. Min Act: -0.0000

Data Index: 1639075 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 3.5541. Min Range: -3.5541

Max Act: 2.8770. Min Act: -0.0000

Data Index: 1613617 (Python Code)

Max Activating Token Index: 753

Text #14

Max Range: 3.5541. Min Range: -3.5541

Max Act: 2.9975. Min Act: -0.0000

Data Index: 1655515 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 3.5541. Min Range: -3.5541

Max Act: 2.9898. Min Act: -0.0000

Data Index: 1553267 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.1171. Min Act: -0.0000

Data Index: 1575793 (Python Code)

Max Activating Token Index: 833

Text #17

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.1049. Min Act: -0.0000

Data Index: 1433175 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 3.5541. Min Range: -3.5541

Max Act: 3.0953. Min Act: -0.0000

Data Index: 1456427 (Python Code)

Max Activating Token Index: 404

Text #19

Max Range: 3.5541. Min Range: -3.5541

Max Act: 2.9421. Min Act: -0.0000

Data Index: 1509066 (Python Code)

Max Activating Token Index: 377