Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5468. Min Act: -0.0000

Data Index: 581879 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1126855 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1353345 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4655. Min Act: -0.0000

Data Index: 571087 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5151. Min Act: -0.0001

Data Index: 812600 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5114. Min Act: -0.0001

Data Index: 47773 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4713. Min Act: -0.0001

Data Index: 299639 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4834. Min Act: -0.0000

Data Index: 968956 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.5145. Min Act: -0.0001

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4433. Min Act: -0.0001

Data Index: 984966 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4658. Min Act: -0.0001

Data Index: 234812 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4558. Min Act: -0.0001

Data Index: 54848 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4387. Min Act: -0.0001

Data Index: 773734 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4728. Min Act: -0.0001

Data Index: 1034775 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4600. Min Act: -0.0001

Data Index: 1100568 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4242. Min Act: -0.0000

Data Index: 596953 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4284. Min Act: -0.0001

Data Index: 70346 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.3977. Min Act: -0.0001

Data Index: 218512 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4437. Min Act: -0.0001

Data Index: 345416 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.5468. Min Range: -0.5468

Max Act: 0.4387. Min Act: -0.0001

Data Index: 1079308 (C4 (Web Text))

Max Activating Token Index: 593