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

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

Neuron 2204 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.4235. Min Act: 0.0000

Data Index: 1214400 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3812. Min Act: 0.0000

Data Index: 240137 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3879. Min Act: 0.0000

Data Index: 941946 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3756. Min Act: -0.0000

Data Index: 144068 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3370. Min Act: -0.0000

Data Index: 244937 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3357. Min Act: -0.0000

Data Index: 240798 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3365. Min Act: -0.0000

Data Index: 696987 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3465. Min Act: 0.0000

Data Index: 417471 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3273. Min Act: -0.0000

Data Index: 281515 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3273. Min Act: -0.0000

Data Index: 111963 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3324. Min Act: 0.0000

Data Index: 683197 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3114. Min Act: 0.0000

Data Index: 774567 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.2970. Min Act: 0.0000

Data Index: 280502 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1335797 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.2755. Min Act: -0.0000

Data Index: 506254 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.2741. Min Act: -0.0000

Data Index: 33096 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1038504 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.2729. Min Act: -0.0000

Data Index: 868180 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.2548. Min Act: -0.0000

Data Index: 567551 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.4235. Min Range: -0.4235

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1245748 (C4 (Web Text))

Max Activating Token Index: 532