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

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

Neuron 111 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.5503. Min Act: -0.0000

Data Index: 574645 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4979. Min Act: -0.0000

Data Index: 83654 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4779. Min Act: -0.0000

Data Index: 281085 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4736. Min Act: -0.0000

Data Index: 786554 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4662. Min Act: -0.0000

Data Index: 535605 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1352641 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4393. Min Act: -0.0000

Data Index: 284050 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4371. Min Act: -0.0000

Data Index: 536687 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1299593 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1169303 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1282736 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4097. Min Act: 0.0000

Data Index: 477405 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4299. Min Act: -0.0000

Data Index: 236170 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4150. Min Act: -0.0000

Data Index: 785133 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4107. Min Act: -0.0000

Data Index: 233668 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4046. Min Act: -0.0000

Data Index: 586586 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.3944. Min Act: -0.0000

Data Index: 730350 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4000. Min Act: -0.0000

Data Index: 224301 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4088. Min Act: -0.0000

Data Index: 55041 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.3807. Min Act: -0.0000

Data Index: 871858 (C4 (Web Text))

Max Activating Token Index: 879