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

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

Neuron 3645 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6596. Min Act: -0.0002

Data Index: 1302783 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5564. Min Act: -0.0002

Data Index: 823650 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5608. Min Act: -0.0002

Data Index: 903548 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5248. Min Act: -0.0002

Data Index: 856121 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5542. Min Act: -0.0002

Data Index: 713655 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5346. Min Act: -0.0002

Data Index: 45751 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5531. Min Act: -0.0002

Data Index: 477261 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5491. Min Act: -0.0002

Data Index: 1101153 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5291. Min Act: -0.0002

Data Index: 39833 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5659. Min Act: -0.0002

Data Index: 552969 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5520. Min Act: -0.0002

Data Index: 855833 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5049. Min Act: -0.0002

Data Index: 1094832 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4976. Min Act: -0.0002

Data Index: 686107 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5075. Min Act: -0.0002

Data Index: 1214499 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4857. Min Act: -0.0002

Data Index: 145479 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4742. Min Act: -0.0002

Data Index: 175174 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4621. Min Act: -0.0002

Data Index: 418096 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5119. Min Act: -0.0002

Data Index: 60652 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4929. Min Act: -0.0002

Data Index: 199788 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4750. Min Act: -0.0002

Data Index: 270208 (C4 (Web Text))

Max Activating Token Index: 291