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

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

Neuron 5343 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8829. Min Range: -4.8829

Max Act: 4.8829. Min Act: 0.0000

Data Index: 1442297 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.7752. Min Act: -0.0000

Data Index: 1619229 (Python Code)

Max Activating Token Index: 875

Text #2

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.5792. Min Act: 0.0000

Data Index: 1375981 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.6875. Min Act: -0.0000

Data Index: 1594359 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.2292. Min Act: 0.0000

Data Index: 1395624 (Python Code)

Max Activating Token Index: 589

Text #5

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.4983. Min Act: 0.0001

Data Index: 1443294 (Python Code)

Max Activating Token Index: 766

Text #6

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.9283. Min Act: 0.0001

Data Index: 1506453 (Python Code)

Max Activating Token Index: 135

Text #7

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.0443. Min Act: 0.0000

Data Index: 1609933 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.0243. Min Act: 0.0000

Data Index: 1570988 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.1249. Min Act: -0.0000

Data Index: 1409677 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.9568. Min Act: -0.0000

Data Index: 1539946 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.9417. Min Act: 0.0001

Data Index: 1529381 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.9164. Min Act: 0.0000

Data Index: 1470453 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.8975. Min Act: -0.0000

Data Index: 1412561 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 4.8829. Min Range: -4.8829

Max Act: 3.0213. Min Act: -0.0000

Data Index: 1650271 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.7323. Min Act: -0.0000

Data Index: 1636705 (Python Code)

Max Activating Token Index: 609

Text #16

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.8575. Min Act: 0.0000

Data Index: 1461784 (Python Code)

Max Activating Token Index: 466

Text #17

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.8329. Min Act: 0.0000

Data Index: 1423440 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.8153. Min Act: 0.0000

Data Index: 1549189 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 4.8829. Min Range: -4.8829

Max Act: 2.8190. Min Act: -0.0000

Data Index: 1420772 (Python Code)

Max Activating Token Index: 28