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

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

Neuron 3026 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: 1.5641. Min Range: -1.5641

Max Act: 1.5641. Min Act: -0.0002

Data Index: 1580719 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.5263. Min Act: -0.0002

Data Index: 1445451 (Python Code)

Max Activating Token Index: 503

Text #2

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3561. Min Act: -0.0002

Data Index: 1561463 (Python Code)

Max Activating Token Index: 271

Text #3

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3733. Min Act: -0.0002

Data Index: 1370074 (Python Code)

Max Activating Token Index: 551

Text #4

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3249. Min Act: -0.0002

Data Index: 1460875 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2879. Min Act: -0.0002

Data Index: 1539773 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2642. Min Act: -0.0002

Data Index: 302073 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2902. Min Act: -0.0002

Data Index: 1480100 (Python Code)

Max Activating Token Index: 515

Text #8

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2800. Min Act: -0.0002

Data Index: 1583805 (Python Code)

Max Activating Token Index: 572

Text #9

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2748. Min Act: -0.0002

Data Index: 1647070 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2418. Min Act: -0.0002

Data Index: 1439214 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2429. Min Act: -0.0002

Data Index: 1596945 (Python Code)

Max Activating Token Index: 264

Text #12

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2209. Min Act: -0.0002

Data Index: 1377846 (Python Code)

Max Activating Token Index: 113

Text #13

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.1962. Min Act: -0.0002

Data Index: 1448623 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.1839. Min Act: -0.0002

Data Index: 1603861 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2022. Min Act: -0.0002

Data Index: 1480645 (Python Code)

Max Activating Token Index: 434

Text #16

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.1879. Min Act: -0.0002

Data Index: 1495055 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.1701. Min Act: -0.0002

Data Index: 1599066 (Python Code)

Max Activating Token Index: 412

Text #18

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.1827. Min Act: -0.0002

Data Index: 1408043 (Python Code)

Max Activating Token Index: 326

Text #19

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.1381. Min Act: -0.0002

Data Index: 1370115 (Python Code)

Max Activating Token Index: 23