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

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

Neuron 2251 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.2842. Min Act: -0.0000

Data Index: 742842 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.2811. Min Act: -0.0000

Data Index: 611876 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1058047 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.2701. Min Act: -0.0000

Data Index: 121731 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.2484. Min Act: -0.0000

Data Index: 437316 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1968. Min Act: -0.0000

Data Index: 546070 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.2163. Min Act: -0.0000

Data Index: 584578 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1001875 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.2185. Min Act: -0.0000

Data Index: 257713 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1927. Min Act: -0.0000

Data Index: 527200 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1877. Min Act: -0.0000

Data Index: 825518 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1739. Min Act: -0.0000

Data Index: 309303 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1494237 (Python Code)

Max Activating Token Index: 183

Text #13

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1767. Min Act: -0.0000

Data Index: 559685 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1801. Min Act: -0.0000

Data Index: 167785 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1563973 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1917. Min Act: -0.0000

Data Index: 824680 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1917. Min Act: -0.0000

Data Index: 935272 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1119740 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.2842. Min Range: -0.2842

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1389927 (Python Code)

Max Activating Token Index: 73