Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1657. Min Range: -2.1657

Max Act: 2.1529. Min Act: -0.0000

Data Index: 752493 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 2.1657. Min Range: -2.1657

Max Act: 2.1657. Min Act: -0.0000

Data Index: 613914 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 2.1657. Min Range: -2.1657

Max Act: 2.0338. Min Act: -0.0000

Data Index: 186898 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.9165. Min Act: -0.0000

Data Index: 1010038 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.7977. Min Act: -0.0000

Data Index: 1256750 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.6432. Min Act: -0.0000

Data Index: 221661 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.2638. Min Act: -0.0000

Data Index: 53322 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.2452. Min Act: -0.0000

Data Index: 5267 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1178911 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1243420 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.1515. Min Act: -0.0000

Data Index: 612863 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.0393. Min Act: -0.0000

Data Index: 75662 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.0526. Min Act: -0.0000

Data Index: 724267 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1141667 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.1904. Min Act: -0.0000

Data Index: 560297 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.0438. Min Act: -0.0000

Data Index: 198785 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 2.1657. Min Range: -2.1657

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1027615 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1124515 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 2.1657. Min Range: -2.1657

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1006305 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 2.1657. Min Range: -2.1657

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1172631 (C4 (Web Text))

Max Activating Token Index: 147