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

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

Neuron 2050 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: 0.9017. Min Range: -0.9017

Max Act: 0.9017. Min Act: -0.0000

Data Index: 28978 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.7198. Min Act: -0.0000

Data Index: 377827 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6487. Min Act: -0.0000

Data Index: 62641 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6071. Min Act: -0.0000

Data Index: 69416 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.5812. Min Act: -0.0000

Data Index: 524096 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1137731 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.5469. Min Act: -0.0000

Data Index: 505250 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4730. Min Act: -0.0000

Data Index: 308693 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4402. Min Act: -0.0000

Data Index: 63772 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4869. Min Act: -0.0000

Data Index: 495898 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4288. Min Act: -0.0000

Data Index: 814202 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4298. Min Act: -0.0000

Data Index: 300580 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1232950 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4726. Min Act: -0.0000

Data Index: 779884 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4152. Min Act: -0.0000

Data Index: 500002 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4190. Min Act: -0.0000

Data Index: 736543 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.3953. Min Act: -0.0000

Data Index: 815920 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1278996 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.3345. Min Act: -0.0000

Data Index: 55415 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.4009. Min Act: 0.0000

Data Index: 20762 (C4 (Web Text))

Max Activating Token Index: 628