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

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

Neuron 5629 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0502. Min Range: -8.0502

Max Act: 8.0502. Min Act: -0.0000

Data Index: 1545347 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 8.0502. Min Range: -8.0502

Max Act: 7.4360. Min Act: -0.0000

Data Index: 1521163 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 8.0502. Min Range: -8.0502

Max Act: 7.5037. Min Act: -0.0000

Data Index: 1578755 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.5734. Min Act: -0.0000

Data Index: 1512127 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.7352. Min Act: -0.0000

Data Index: 1535854 (Python Code)

Max Activating Token Index: 282

Text #5

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.3506. Min Act: -0.0000

Data Index: 1489770 (Python Code)

Max Activating Token Index: 277

Text #6

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.3147. Min Act: -0.0000

Data Index: 1638702 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.0714. Min Act: -0.0000

Data Index: 1403233 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.5172. Min Act: -0.0000

Data Index: 1388240 (Python Code)

Max Activating Token Index: 472

Text #9

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.4705. Min Act: -0.0000

Data Index: 1472514 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 8.0502. Min Range: -8.0502

Max Act: 5.7536. Min Act: -0.0000

Data Index: 1567998 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.4612. Min Act: -0.0000

Data Index: 1530867 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.7707. Min Act: -0.0000

Data Index: 1568131 (Python Code)

Max Activating Token Index: 63

Text #13

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.1751. Min Act: -0.0000

Data Index: 1420995 (Python Code)

Max Activating Token Index: 103

Text #14

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.5199. Min Act: -0.0000

Data Index: 1495208 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.4932. Min Act: -0.0000

Data Index: 1505051 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.4733. Min Act: -0.0000

Data Index: 1648395 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.8187. Min Act: -0.0000

Data Index: 1367100 (Python Code)

Max Activating Token Index: 282

Text #18

Max Range: 8.0502. Min Range: -8.0502

Max Act: 5.8142. Min Act: -0.0000

Data Index: 1416826 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 8.0502. Min Range: -8.0502

Max Act: 6.0461. Min Act: -0.0000

Data Index: 1407738 (Python Code)

Max Activating Token Index: 169