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

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

Neuron 5236 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1369693 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1613319 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1584575 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1434044 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1552427 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1512647 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1448540 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1445480 (Python Code)

Max Activating Token Index: 530

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1379639 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1571590 (Python Code)

Max Activating Token Index: 663

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1396616 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1559833 (Python Code)

Max Activating Token Index: 624

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1389354 (Python Code)

Max Activating Token Index: 946

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1529046 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1428616 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1527655 (Python Code)

Max Activating Token Index: 761

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1426804 (Python Code)

Max Activating Token Index: 362

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1557736 (Python Code)

Max Activating Token Index: 732

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1502250 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1629066 (Python Code)

Max Activating Token Index: 725