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

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

Neuron 4422 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1332010 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.3529. Min Act: -0.0000

Data Index: 422444 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.3562. Min Act: -0.0000

Data Index: 372989 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2957. Min Act: -0.0000

Data Index: 993522 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2859. Min Act: -0.0000

Data Index: 347410 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2980. Min Act: -0.0000

Data Index: 190935 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2810. Min Act: 0.0002

Data Index: 739930 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2895. Min Act: -0.0000

Data Index: 931255 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2840. Min Act: 0.0001

Data Index: 360258 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2809. Min Act: -0.0000

Data Index: 121254 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2793. Min Act: -0.0000

Data Index: 90151 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2773. Min Act: -0.0000

Data Index: 213829 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1282873 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2672. Min Act: -0.0000

Data Index: 653708 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2800. Min Act: -0.0000

Data Index: 15740 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2736. Min Act: -0.0000

Data Index: 929042 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1100339 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2655. Min Act: -0.0000

Data Index: 145489 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1255119 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1005916 (C4 (Web Text))

Max Activating Token Index: 435