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

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

Neuron 953 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: 1.2014. Min Range: -1.2014

Max Act: 1.2014. Min Act: -0.0000

Data Index: 698398 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.2014. Min Range: -1.2014

Max Act: 1.1056. Min Act: -0.0000

Data Index: 305450 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.9989. Min Act: -0.0000

Data Index: 546471 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 1.2014. Min Range: -1.2014

Max Act: 1.0250. Min Act: -0.0000

Data Index: 525375 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.8470. Min Act: -0.0000

Data Index: 767617 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.8664. Min Act: -0.0000

Data Index: 582201 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.8379. Min Act: -0.0000

Data Index: 537256 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.8318. Min Act: -0.0000

Data Index: 57387 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.8226. Min Act: -0.0000

Data Index: 214668 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.8550. Min Act: -0.0000

Data Index: 790147 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.7711. Min Act: -0.0000

Data Index: 768181 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.8070. Min Act: -0.0000

Data Index: 986573 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.8024. Min Act: -0.0000

Data Index: 664533 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.7738. Min Act: -0.0000

Data Index: 601469 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1178974 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.7613. Min Act: -0.0000

Data Index: 240248 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1217061 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.7329. Min Act: -0.0000

Data Index: 421448 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.7521. Min Act: -0.0000

Data Index: 986753 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.2014. Min Range: -1.2014

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1179083 (C4 (Web Text))

Max Activating Token Index: 868