Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 943 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6747. Min Act: -0.0001

Data Index: 544987 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6573. Min Act: -0.0001

Data Index: 1210628 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5983. Min Act: -0.0001

Data Index: 259510 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5655. Min Act: -0.0001

Data Index: 743504 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5454. Min Act: -0.0001

Data Index: 1273875 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5406. Min Act: -0.0001

Data Index: 1074325 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6122. Min Act: -0.0001

Data Index: 739882 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5769. Min Act: -0.0002

Data Index: 90470 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5507. Min Act: -0.0001

Data Index: 1268515 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1212093 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5522. Min Act: -0.0002

Data Index: 1179591 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5454. Min Act: -0.0002

Data Index: 348743 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1193869 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5416. Min Act: -0.0001

Data Index: 916601 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5761. Min Act: -0.0001

Data Index: 735010 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5307. Min Act: -0.0002

Data Index: 118551 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5470. Min Act: -0.0002

Data Index: 15385 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5830. Min Act: -0.0002

Data Index: 968366 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5058. Min Act: -0.0001

Data Index: 823145 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5378. Min Act: -0.0002

Data Index: 1095175 (C4 (Web Text))

Max Activating Token Index: 714