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

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

Neuron 827 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1049. Min Act: -0.0000

Data Index: 886551 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1139537 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0902. Min Act: -0.0000

Data Index: 152104 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1412131 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1015363 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0832. Min Act: -0.0000

Data Index: 37537 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1453820 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0767. Min Act: -0.0000

Data Index: 348999 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0817. Min Act: -0.0000

Data Index: 577640 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0808. Min Act: -0.0000

Data Index: 888165 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1622102 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0815. Min Act: -0.0000

Data Index: 325081 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1060024 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0782. Min Act: -0.0000

Data Index: 25530 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1075542 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0768. Min Act: -0.0000

Data Index: 329722 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0839. Min Act: -0.0000

Data Index: 479173 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0770. Min Act: -0.0000

Data Index: 796127 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1072958 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1008241 (C4 (Web Text))

Max Activating Token Index: 773