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

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

Neuron 3018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4982. Min Act: -0.0000

Data Index: 282880 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4979. Min Act: -0.0000

Data Index: 817130 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4730. Min Act: -0.0000

Data Index: 519019 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4457. Min Act: -0.0000

Data Index: 144401 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4166. Min Act: -0.0000

Data Index: 962247 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1077319 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3858. Min Act: -0.0000

Data Index: 307040 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3938. Min Act: -0.0000

Data Index: 846340 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3931. Min Act: -0.0000

Data Index: 636130 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4017. Min Act: -0.0000

Data Index: 382058 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3511. Min Act: -0.0000

Data Index: 16018 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3814. Min Act: -0.0000

Data Index: 262819 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3892. Min Act: -0.0000

Data Index: 131357 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3738. Min Act: -0.0000

Data Index: 26865 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3828. Min Act: -0.0000

Data Index: 392905 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1135964 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3749. Min Act: -0.0000

Data Index: 630906 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3575. Min Act: -0.0000

Data Index: 499566 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1174198 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3565. Min Act: -0.0000

Data Index: 443374 (C4 (Web Text))

Max Activating Token Index: 722