Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 311 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0002

Data Index: 727537 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1322. Min Act: -0.0002

Data Index: 1448236 (Python Code)

Max Activating Token Index: 763

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1370. Min Act: -0.0002

Data Index: 1403128 (Python Code)

Max Activating Token Index: 412

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1041272 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1266. Min Act: -0.0002

Data Index: 1376211 (Python Code)

Max Activating Token Index: 460

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1585786 (Python Code)

Max Activating Token Index: 638

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1324336 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1126. Min Act: -0.0001

Data Index: 819538 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1421822 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1057. Min Act: -0.0002

Data Index: 584023 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1393421 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1064. Min Act: -0.0001

Data Index: 360192 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.0995. Min Act: -0.0002

Data Index: 103243 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1057. Min Act: -0.0002

Data Index: 40398 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1023. Min Act: -0.0002

Data Index: 904038 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1039. Min Act: -0.0002

Data Index: 864070 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.0954. Min Act: -0.0002

Data Index: 995811 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1516413 (Python Code)

Max Activating Token Index: 387

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1077. Min Act: -0.0002

Data Index: 221438 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1035. Min Act: -0.0002

Data Index: 141276 (C4 (Web Text))

Max Activating Token Index: 533