Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1800 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.0096. Min Range: -8.0096

Max Act: 8.0096. Min Act: -0.0000

Data Index: 673252 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 8.0096. Min Range: -8.0096

Max Act: 7.5101. Min Act: -0.0000

Data Index: 743062 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 8.0096. Min Range: -8.0096

Max Act: 7.0433. Min Act: -0.0000

Data Index: 54803 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.7989. Min Act: -0.0000

Data Index: 1252046 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.9205. Min Act: -0.0000

Data Index: 972835 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.7675. Min Act: -0.0000

Data Index: 445392 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.6856. Min Act: -0.0000

Data Index: 839270 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.6868. Min Act: -0.0000

Data Index: 141541 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.2915. Min Act: -0.0000

Data Index: 156745 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 8.0096. Min Range: -8.0096

Max Act: 5.8479. Min Act: -0.0000

Data Index: 856248 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 8.0096. Min Range: -8.0096

Max Act: 5.9390. Min Act: -0.0000

Data Index: 74741 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.0739. Min Act: -0.0000

Data Index: 455472 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.1093. Min Act: -0.0000

Data Index: 838371 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 8.0096. Min Range: -8.0096

Max Act: 6.0432. Min Act: -0.0000

Data Index: 619508 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 8.0096. Min Range: -8.0096

Max Act: 5.7979. Min Act: -0.0000

Data Index: 214345 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 8.0096. Min Range: -8.0096

Max Act: 5.6001. Min Act: -0.0000

Data Index: 964749 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 8.0096. Min Range: -8.0096

Max Act: 5.5939. Min Act: -0.0000

Data Index: 741283 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 8.0096. Min Range: -8.0096

Max Act: 5.5483. Min Act: -0.0000

Data Index: 903306 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 8.0096. Min Range: -8.0096

Max Act: 5.9028. Min Act: -0.0000

Data Index: 473735 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 8.0096. Min Range: -8.0096

Max Act: 5.7117. Min Act: -0.0000

Data Index: 1038477 (C4 (Web Text))

Max Activating Token Index: 271