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

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

Neuron 2943 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: 1.8715. Min Range: -1.8715

Max Act: 1.8715. Min Act: -0.0002

Data Index: 560271 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.8211. Min Act: -0.0002

Data Index: 1261130 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6898. Min Act: -0.0002

Data Index: 1600972 (Python Code)

Max Activating Token Index: 963

Text #3

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6205. Min Act: -0.0002

Data Index: 1549709 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6217. Min Act: -0.0002

Data Index: 1633519 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5703. Min Act: -0.0002

Data Index: 1592566 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6137. Min Act: -0.0002

Data Index: 1493915 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5544. Min Act: -0.0002

Data Index: 1594184 (Python Code)

Max Activating Token Index: 333

Text #8

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5449. Min Act: -0.0002

Data Index: 1373629 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5596. Min Act: -0.0002

Data Index: 1653928 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5181. Min Act: -0.0002

Data Index: 1425564 (Python Code)

Max Activating Token Index: 841

Text #11

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5363. Min Act: -0.0002

Data Index: 1613787 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5096. Min Act: -0.0002

Data Index: 1421596 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5488. Min Act: -0.0002

Data Index: 1475089 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.4933. Min Act: -0.0002

Data Index: 1534971 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5137. Min Act: -0.0002

Data Index: 1637176 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5248. Min Act: -0.0002

Data Index: 1516868 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5001. Min Act: -0.0002

Data Index: 1558650 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5313. Min Act: -0.0002

Data Index: 1651370 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.4280. Min Act: -0.0002

Data Index: 1517047 (Python Code)

Max Activating Token Index: 881