Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 473 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0063. Min Act: -0.0006

Data Index: 542877 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0006

Data Index: 816087 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1083505 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1131587 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0006

Data Index: 588080 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0005

Data Index: 156809 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0006

Data Index: 485359 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1114984 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0006

Data Index: 151439 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0006

Data Index: 253930 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0006

Data Index: 428237 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0006

Data Index: 508092 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0005

Data Index: 136008 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1303128 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0006

Data Index: 121465 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0006

Data Index: 182311 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0006

Data Index: 539578 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0005

Data Index: 811682 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0005

Data Index: 530377 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0006

Data Index: 203480 (C4 (Web Text))

Max Activating Token Index: 393