Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1547 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.9721. Min Act: -0.0000

Data Index: 834101 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 1.0894. Min Range: -1.0894

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1236464 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.0894. Min Range: -1.0894

Max Act: 1.0073. Min Act: -0.0000

Data Index: 422807 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.9289. Min Act: -0.0000

Data Index: 695089 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.9174. Min Act: -0.0000

Data Index: 699477 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.8019. Min Act: -0.0000

Data Index: 933960 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.8690. Min Act: 0.0000

Data Index: 1474832 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.8926. Min Act: 0.0000

Data Index: 1630546 (Python Code)

Max Activating Token Index: 731

Text #8

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.8338. Min Act: 0.0000

Data Index: 1519009 (Python Code)

Max Activating Token Index: 419

Text #9

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.8357. Min Act: -0.0000

Data Index: 688184 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.7773. Min Act: -0.0000

Data Index: 806042 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.7286. Min Act: -0.0000

Data Index: 776059 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.7907. Min Act: -0.0000

Data Index: 698639 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.7612. Min Act: -0.0000

Data Index: 44767 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.7592. Min Act: -0.0000

Data Index: 287961 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.7790. Min Act: -0.0000

Data Index: 696245 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.7088. Min Act: -0.0000

Data Index: 73541 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.7458. Min Act: -0.0000

Data Index: 738972 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.6650. Min Act: 0.0000

Data Index: 1437760 (Python Code)

Max Activating Token Index: 501

Text #19

Max Range: 1.0894. Min Range: -1.0894

Max Act: 0.6311. Min Act: -0.0000

Data Index: 141760 (C4 (Web Text))

Max Activating Token Index: 554