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

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

Neuron 797 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: 0.6510. Min Range: -0.6510

Max Act: 0.6510. Min Act: -0.0000

Data Index: 650475 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5723. Min Act: -0.0000

Data Index: 377316 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5608. Min Act: -0.0000

Data Index: 400171 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.6060. Min Act: -0.0000

Data Index: 226959 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5807. Min Act: 0.0000

Data Index: 1102962 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5590. Min Act: -0.0000

Data Index: 51888 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1333320 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5504. Min Act: -0.0000

Data Index: 969392 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1325723 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5149. Min Act: 0.0000

Data Index: 605970 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1019849 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5168. Min Act: -0.0000

Data Index: 4276 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5108. Min Act: 0.0001

Data Index: 466871 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.4988. Min Act: 0.0000

Data Index: 169931 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1331863 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1081366 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5095. Min Act: -0.0000

Data Index: 494245 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5046. Min Act: 0.0000

Data Index: 296231 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.4995. Min Act: 0.0001

Data Index: 520877 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.4982. Min Act: -0.0000

Data Index: 880710 (C4 (Web Text))

Max Activating Token Index: 429