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

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

Neuron 5388 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.7579. Min Act: -0.0002

Data Index: 1401595 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.6628. Min Act: -0.0002

Data Index: 1442774 (Python Code)

Max Activating Token Index: 723

Text #2

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.5802. Min Act: -0.0002

Data Index: 1465762 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.6059. Min Act: -0.0002

Data Index: 1387030 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.5719. Min Act: -0.0002

Data Index: 1415973 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.5629. Min Act: -0.0002

Data Index: 1617371 (Python Code)

Max Activating Token Index: 738

Text #6

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.5053. Min Act: -0.0002

Data Index: 1429414 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.5077. Min Act: -0.0002

Data Index: 1616847 (Python Code)

Max Activating Token Index: 296

Text #8

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4603. Min Act: -0.0002

Data Index: 1393947 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4456. Min Act: -0.0002

Data Index: 1489884 (Python Code)

Max Activating Token Index: 913

Text #10

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4524. Min Act: -0.0002

Data Index: 1528098 (Python Code)

Max Activating Token Index: 418

Text #11

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4690. Min Act: -0.0002

Data Index: 1474988 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4137. Min Act: -0.0002

Data Index: 1440649 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4390. Min Act: -0.0002

Data Index: 1481697 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4682. Min Act: -0.0002

Data Index: 1478073 (Python Code)

Max Activating Token Index: 798

Text #15

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4166. Min Act: -0.0002

Data Index: 1652131 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.4251. Min Act: -0.0002

Data Index: 1511363 (Python Code)

Max Activating Token Index: 134

Text #17

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.3883. Min Act: -0.0002

Data Index: 1418088 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.3987. Min Act: -0.0002

Data Index: 1594436 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 1.7579. Min Range: -1.7579

Max Act: 1.3606. Min Act: -0.0002

Data Index: 1553506 (Python Code)

Max Activating Token Index: 195