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

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

Neuron 2354 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3230. Min Range: -1.3230

Max Act: 1.3230. Min Act: -0.0001

Data Index: 372617 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.9527. Min Act: -0.0001

Data Index: 1038771 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.8082. Min Act: -0.0001

Data Index: 675206 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.7306. Min Act: -0.0001

Data Index: 710649 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.6346. Min Act: -0.0001

Data Index: 1014882 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.6144. Min Act: -0.0001

Data Index: 547889 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5861. Min Act: -0.0001

Data Index: 587219 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.6514. Min Act: -0.0001

Data Index: 1354178 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5998. Min Act: -0.0001

Data Index: 1075252 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5996. Min Act: -0.0001

Data Index: 283272 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.6400. Min Act: -0.0001

Data Index: 1380108 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5702. Min Act: -0.0001

Data Index: 1046863 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.6300. Min Act: -0.0001

Data Index: 77739 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.6212. Min Act: -0.0001

Data Index: 714383 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5796. Min Act: -0.0001

Data Index: 826108 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5363. Min Act: -0.0001

Data Index: 418701 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.4821. Min Act: -0.0001

Data Index: 372631 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5098. Min Act: -0.0001

Data Index: 901680 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5651. Min Act: -0.0001

Data Index: 139286 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.5440. Min Act: -0.0001

Data Index: 559600 (C4 (Web Text))

Max Activating Token Index: 409