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

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

Neuron 1497 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4363. Min Range: -4.4363

Max Act: 4.4363. Min Act: -0.0000

Data Index: 1456277 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 4.4363. Min Range: -4.4363

Max Act: 4.1976. Min Act: -0.0000

Data Index: 1510302 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.6551. Min Act: -0.0000

Data Index: 1494487 (Python Code)

Max Activating Token Index: 784

Text #3

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.7183. Min Act: -0.0000

Data Index: 1514588 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.5888. Min Act: -0.0000

Data Index: 1362634 (Python Code)

Max Activating Token Index: 428

Text #5

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.7030. Min Act: -0.0000

Data Index: 1456842 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.6937. Min Act: -0.0000

Data Index: 1447911 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.5027. Min Act: -0.0000

Data Index: 1652380 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.2669. Min Act: -0.0000

Data Index: 1408409 (Python Code)

Max Activating Token Index: 760

Text #9

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.3480. Min Act: -0.0000

Data Index: 1490815 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.4468. Min Act: -0.0000

Data Index: 1430425 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.3703. Min Act: -0.0000

Data Index: 1477514 (Python Code)

Max Activating Token Index: 447

Text #12

Max Range: 4.4363. Min Range: -4.4363

Max Act: 2.9879. Min Act: -0.0000

Data Index: 1453946 (Python Code)

Max Activating Token Index: 388

Text #13

Max Range: 4.4363. Min Range: -4.4363

Max Act: 2.9946. Min Act: -0.0000

Data Index: 1587708 (Python Code)

Max Activating Token Index: 498

Text #14

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.1512. Min Act: -0.0000

Data Index: 1418454 (Python Code)

Max Activating Token Index: 490

Text #15

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.2698. Min Act: -0.0000

Data Index: 1377706 (Python Code)

Max Activating Token Index: 525

Text #16

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.2434. Min Act: -0.0000

Data Index: 1618382 (Python Code)

Max Activating Token Index: 857

Text #17

Max Range: 4.4363. Min Range: -4.4363

Max Act: 3.0948. Min Act: -0.0000

Data Index: 1640422 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 4.4363. Min Range: -4.4363

Max Act: 2.5982. Min Act: -0.0000

Data Index: 1388182 (Python Code)

Max Activating Token Index: 717

Text #19

Max Range: 4.4363. Min Range: -4.4363

Max Act: 2.8317. Min Act: -0.0000

Data Index: 1531987 (Python Code)

Max Activating Token Index: 78