Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3049 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0003

Data Index: 442346 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1002522 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0063. Min Act: -0.0003

Data Index: 835631 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0003

Data Index: 839214 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1189838 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0062. Min Act: -0.0003

Data Index: 608155 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0003

Data Index: 666635 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0003

Data Index: 355952 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1000784 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 499567 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 441969 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 117226 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 33048 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1236788 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1211341 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0003

Data Index: 553590 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 987870 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0002

Data Index: 780458 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1119573 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1005676 (C4 (Web Text))

Max Activating Token Index: 746