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

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

Neuron 100 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.6836. Min Act: -0.0003

Data Index: 1418320 (Python Code)

Max Activating Token Index: 482

Text #1

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.4598. Min Act: -0.0003

Data Index: 1505406 (Python Code)

Max Activating Token Index: 509

Text #2

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5073. Min Act: -0.0003

Data Index: 1578110 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.6718. Min Act: -0.0003

Data Index: 1458354 (Python Code)

Max Activating Token Index: 313

Text #4

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.6967. Min Act: -0.0003

Data Index: 1586836 (Python Code)

Max Activating Token Index: 735

Text #5

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5573. Min Act: -0.0003

Data Index: 1381044 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.6804. Min Act: -0.0003

Data Index: 1418132 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5416. Min Act: -0.0003

Data Index: 1520209 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.6312. Min Act: -0.0003

Data Index: 1526147 (Python Code)

Max Activating Token Index: 709

Text #9

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5065. Min Act: -0.0003

Data Index: 1561565 (Python Code)

Max Activating Token Index: 583

Text #10

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5191. Min Act: -0.0003

Data Index: 1578393 (Python Code)

Max Activating Token Index: 515

Text #11

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.7465. Min Act: -0.0003

Data Index: 1585409 (Python Code)

Max Activating Token Index: 485

Text #12

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5899. Min Act: -0.0003

Data Index: 1460885 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5430. Min Act: -0.0003

Data Index: 1450881 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.4022. Min Act: -0.0003

Data Index: 1394007 (Python Code)

Max Activating Token Index: 357

Text #15

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.4630. Min Act: -0.0003

Data Index: 1368286 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.4140. Min Act: -0.0003

Data Index: 1456827 (Python Code)

Max Activating Token Index: 709

Text #17

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.5173. Min Act: -0.0003

Data Index: 1646143 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.3899. Min Act: -0.0003

Data Index: 1401356 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 1.7465. Min Range: -1.7465

Max Act: 1.3796. Min Act: -0.0003

Data Index: 1401148 (Python Code)

Max Activating Token Index: 559