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

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

Neuron 3199 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5731. Min Range: -2.5731

Max Act: 2.5731. Min Act: -0.0000

Data Index: 1502317 (Python Code)

Max Activating Token Index: 741

Text #1

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.9857. Min Act: -0.0000

Data Index: 1506469 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.9400. Min Act: -0.0000

Data Index: 1390690 (Python Code)

Max Activating Token Index: 882

Text #3

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.8946. Min Act: -0.0000

Data Index: 464424 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.7802. Min Act: -0.0000

Data Index: 1580553 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1585845 (Python Code)

Max Activating Token Index: 716

Text #6

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.7186. Min Act: -0.0000

Data Index: 1436734 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1524745 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.4889. Min Act: -0.0000

Data Index: 1428091 (Python Code)

Max Activating Token Index: 513

Text #9

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.4702. Min Act: -0.0000

Data Index: 1652925 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.5327. Min Act: -0.0000

Data Index: 1395866 (Python Code)

Max Activating Token Index: 444

Text #11

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1532673 (Python Code)

Max Activating Token Index: 447

Text #12

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.4976. Min Act: -0.0000

Data Index: 1262146 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1485383 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.5654. Min Act: -0.0000

Data Index: 1645203 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1549618 (Python Code)

Max Activating Token Index: 938

Text #16

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1526538 (Python Code)

Max Activating Token Index: 916

Text #17

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.3640. Min Act: -0.0000

Data Index: 1378819 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1652846 (Python Code)

Max Activating Token Index: 667

Text #19

Max Range: 2.5731. Min Range: -2.5731

Max Act: 1.4335. Min Act: -0.0000

Data Index: 1554237 (Python Code)

Max Activating Token Index: 141