Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2270 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.9509. Min Act: -0.0001

Data Index: 136880 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8694. Min Act: -0.0001

Data Index: 1542452 (Python Code)

Max Activating Token Index: 202

Text #2

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8801. Min Act: -0.0001

Data Index: 248235 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8354. Min Act: -0.0001

Data Index: 1588117 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1630987 (Python Code)

Max Activating Token Index: 349

Text #5

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1647141 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1300018 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8631. Min Act: -0.0001

Data Index: 705209 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7867. Min Act: -0.0001

Data Index: 1534306 (Python Code)

Max Activating Token Index: 330

Text #9

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1563917 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7556. Min Act: -0.0001

Data Index: 1376584 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1551792 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7564. Min Act: -0.0001

Data Index: 1130159 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7080. Min Act: -0.0001

Data Index: 1526854 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.6939. Min Act: -0.0001

Data Index: 1519646 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.6726. Min Act: -0.0001

Data Index: 1597077 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7335. Min Act: -0.0001

Data Index: 1430319 (Python Code)

Max Activating Token Index: 440

Text #17

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1506793 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7442. Min Act: -0.0001

Data Index: 1613759 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7015. Min Act: -0.0001

Data Index: 1577159 (Python Code)

Max Activating Token Index: 306