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

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

Neuron 1408 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: 0.1027. Min Range: -0.1027

Max Act: 0.1027. Min Act: -0.0001

Data Index: 485125 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0822. Min Act: -0.0001

Data Index: 678043 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0920. Min Act: -0.0001

Data Index: 102549 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1030792 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0889. Min Act: -0.0001

Data Index: 386949 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0905. Min Act: -0.0001

Data Index: 914497 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0880. Min Act: -0.0000

Data Index: 513340 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0924. Min Act: -0.0001

Data Index: 452262 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0920. Min Act: -0.0001

Data Index: 42831 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0858. Min Act: -0.0001

Data Index: 22989 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0865. Min Act: -0.0001

Data Index: 517464 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1023044 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0834. Min Act: -0.0001

Data Index: 293418 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0829. Min Act: -0.0001

Data Index: 909161 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0861. Min Act: -0.0001

Data Index: 435446 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0816. Min Act: -0.0001

Data Index: 437461 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1146974 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0809. Min Act: -0.0001

Data Index: 718322 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0806. Min Act: -0.0001

Data Index: 733679 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0797. Min Act: -0.0001

Data Index: 46021 (C4 (Web Text))

Max Activating Token Index: 884