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

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

Neuron 2019 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.6391. Min Act: -0.0000

Data Index: 846257 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5866. Min Act: -0.0000

Data Index: 919869 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5593. Min Act: -0.0000

Data Index: 281793 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5498. Min Act: -0.0000

Data Index: 211297 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5338. Min Act: -0.0000

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1224566 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5198. Min Act: -0.0000

Data Index: 827591 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4908. Min Act: -0.0000

Data Index: 268061 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4951. Min Act: -0.0000

Data Index: 683127 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5177. Min Act: -0.0000

Data Index: 624397 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4699. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4838. Min Act: -0.0000

Data Index: 225204 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.5001. Min Act: -0.0000

Data Index: 748208 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4500. Min Act: -0.0000

Data Index: 491103 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1307549 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4582. Min Act: -0.0000

Data Index: 811213 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4654. Min Act: -0.0000

Data Index: 733206 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1252129 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4606. Min Act: -0.0000

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.6391. Min Range: -0.6391

Max Act: 0.4557. Min Act: -0.0000

Data Index: 396527 (C4 (Web Text))

Max Activating Token Index: 916