Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1678 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1149458 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0001

Data Index: 309454 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1203033 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0718. Min Act: -0.0001

Data Index: 322268 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0778. Min Act: -0.0001

Data Index: 455045 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0780. Min Act: -0.0001

Data Index: 44325 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0697. Min Act: -0.0001

Data Index: 964186 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0715. Min Act: -0.0001

Data Index: 645914 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1243866 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0637. Min Act: -0.0001

Data Index: 118445 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1092033 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0713. Min Act: -0.0001

Data Index: 609548 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0694. Min Act: -0.0001

Data Index: 71694 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0734. Min Act: -0.0001

Data Index: 834305 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0682. Min Act: -0.0001

Data Index: 356158 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0656. Min Act: -0.0001

Data Index: 876411 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0675. Min Act: -0.0001

Data Index: 997105 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0629. Min Act: -0.0001

Data Index: 978969 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0671. Min Act: -0.0001

Data Index: 886455 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0672. Min Act: -0.0001

Data Index: 937993 (C4 (Web Text))

Max Activating Token Index: 123