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

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

Neuron 3500 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0635. Min Range: -4.0635

Max Act: 4.0635. Min Act: 0.0001

Data Index: 1635040 (Python Code)

Max Activating Token Index: 317

Text #1

Max Range: 4.0635. Min Range: -4.0635

Max Act: 4.0326. Min Act: 0.0001

Data Index: 1634503 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.9031. Min Act: -0.0000

Data Index: 1644918 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.5650. Min Act: -0.0000

Data Index: 1621899 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.6571. Min Act: 0.0001

Data Index: 1631146 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.6376. Min Act: -0.0000

Data Index: 1510322 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.4775. Min Act: -0.0000

Data Index: 1405489 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.3026. Min Act: -0.0000

Data Index: 1572423 (Python Code)

Max Activating Token Index: 409

Text #8

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.5751. Min Act: -0.0000

Data Index: 1406298 (Python Code)

Max Activating Token Index: 810

Text #9

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.4051. Min Act: -0.0000

Data Index: 1433980 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.4039. Min Act: -0.0000

Data Index: 1582007 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.2592. Min Act: -0.0000

Data Index: 1555279 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.2729. Min Act: 0.0001

Data Index: 1565308 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.0798. Min Act: 0.0000

Data Index: 1392398 (Python Code)

Max Activating Token Index: 692

Text #14

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.2160. Min Act: 0.0000

Data Index: 1561624 (Python Code)

Max Activating Token Index: 200

Text #15

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.1751. Min Act: 0.0000

Data Index: 1544724 (Python Code)

Max Activating Token Index: 718

Text #16

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.2796. Min Act: 0.0001

Data Index: 1384486 (Python Code)

Max Activating Token Index: 675

Text #17

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.1160. Min Act: 0.0001

Data Index: 1570577 (Python Code)

Max Activating Token Index: 438

Text #18

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.2267. Min Act: -0.0000

Data Index: 1487501 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.0807. Min Act: -0.0000

Data Index: 1654496 (Python Code)

Max Activating Token Index: 332