Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1989 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4471. Min Act: -0.0001

Data Index: 1390922 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1551897 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1611510 (Python Code)

Max Activating Token Index: 349

Text #3

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4440. Min Act: -0.0001

Data Index: 1616015 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4105. Min Act: -0.0001

Data Index: 1485710 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1505817 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4197. Min Act: -0.0001

Data Index: 1508223 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4197. Min Act: -0.0001

Data Index: 1403029 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4006. Min Act: -0.0001

Data Index: 1565116 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3975. Min Act: -0.0001

Data Index: 1507653 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1572559 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3683. Min Act: -0.0001

Data Index: 1491728 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1575040 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1633920 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.4011. Min Act: -0.0001

Data Index: 1446773 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1560994 (Python Code)

Max Activating Token Index: 129

Text #16

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1646089 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3715. Min Act: -0.0001

Data Index: 1577000 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3703. Min Act: -0.0001

Data Index: 1622451 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 0.4471. Min Range: -0.4471

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1421344 (Python Code)

Max Activating Token Index: 356