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

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

Neuron 4251 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: 0.7595. Min Range: -0.7595

Max Act: 0.7595. Min Act: -0.0000

Data Index: 286404 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6352. Min Act: -0.0000

Data Index: 17454 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5712. Min Act: -0.0000

Data Index: 445007 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5629. Min Act: -0.0000

Data Index: 160565 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5571. Min Act: -0.0000

Data Index: 387972 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5335. Min Act: -0.0000

Data Index: 365616 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5520. Min Act: -0.0000

Data Index: 438895 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1035638 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5445. Min Act: -0.0000

Data Index: 542264 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5290. Min Act: -0.0000

Data Index: 687785 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5194. Min Act: -0.0000

Data Index: 39683 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5275. Min Act: -0.0000

Data Index: 556880 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5005. Min Act: -0.0000

Data Index: 169569 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5061. Min Act: -0.0000

Data Index: 819533 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.4970. Min Act: -0.0000

Data Index: 877777 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.4949. Min Act: -0.0000

Data Index: 170309 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5008. Min Act: -0.0000

Data Index: 58827 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.4995. Min Act: -0.0000

Data Index: 246043 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.4655. Min Act: -0.0000

Data Index: 663429 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.4699. Min Act: -0.0000

Data Index: 802079 (C4 (Web Text))

Max Activating Token Index: 954