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

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

Neuron 3529 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1583268 (Python Code)

Max Activating Token Index: 894

Text #1

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4267. Min Act: -0.0001

Data Index: 1361265 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1404373 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4383. Min Act: -0.0001

Data Index: 1361879 (Python Code)

Max Activating Token Index: 18

Text #4

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4238. Min Act: -0.0001

Data Index: 1445811 (Python Code)

Max Activating Token Index: 896

Text #5

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4243. Min Act: -0.0001

Data Index: 1399408 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4346. Min Act: -0.0001

Data Index: 1564725 (Python Code)

Max Activating Token Index: 389

Text #7

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4135. Min Act: -0.0001

Data Index: 1580223 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4216. Min Act: -0.0001

Data Index: 1486593 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4400. Min Act: -0.0001

Data Index: 1516947 (Python Code)

Max Activating Token Index: 380

Text #10

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4227. Min Act: -0.0001

Data Index: 1614057 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4016. Min Act: -0.0001

Data Index: 1438648 (Python Code)

Max Activating Token Index: 254

Text #12

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4012. Min Act: -0.0001

Data Index: 1428531 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3871. Min Act: -0.0001

Data Index: 1526025 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1535827 (Python Code)

Max Activating Token Index: 739

Text #15

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4115. Min Act: -0.0001

Data Index: 1493780 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4117. Min Act: -0.0001

Data Index: 1643272 (Python Code)

Max Activating Token Index: 568

Text #17

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4074. Min Act: -0.0001

Data Index: 1529418 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4090. Min Act: -0.0001

Data Index: 1386568 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4352. Min Act: -0.0001

Data Index: 1482632 (Python Code)

Max Activating Token Index: 581