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

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

Neuron 4288 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0892. Min Act: -0.0001

Data Index: 946584 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0911. Min Act: -0.0001

Data Index: 81108 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1401125 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1562064 (Python Code)

Max Activating Token Index: 626

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0884. Min Act: -0.0001

Data Index: 334005 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0780. Min Act: -0.0001

Data Index: 581901 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1286518 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1069215 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0818. Min Act: -0.0001

Data Index: 990226 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1036120 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0001

Data Index: 257481 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1485576 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1371994 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1464627 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0826. Min Act: -0.0001

Data Index: 366647 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0823. Min Act: -0.0001

Data Index: 733791 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1604483 (Python Code)

Max Activating Token Index: 593

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1455524 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0777. Min Act: -0.0001

Data Index: 310855 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0798. Min Act: -0.0001

Data Index: 487464 (C4 (Web Text))

Max Activating Token Index: 237