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

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

Neuron 3009 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.6336. Min Act: -0.0001

Data Index: 297213 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.6242. Min Act: -0.0001

Data Index: 923075 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1253503 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.5779. Min Act: -0.0000

Data Index: 1553633 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.5255. Min Act: -0.0001

Data Index: 1566913 (Python Code)

Max Activating Token Index: 963

Text #5

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.5012. Min Act: -0.0000

Data Index: 950089 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.4799. Min Act: -0.0001

Data Index: 1600069 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.5412. Min Act: -0.0001

Data Index: 561533 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.5130. Min Act: -0.0001

Data Index: 1487306 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.4895. Min Act: -0.0001

Data Index: 690945 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.4424. Min Act: -0.0001

Data Index: 1480462 (Python Code)

Max Activating Token Index: 1011

Text #11

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.4306. Min Act: -0.0000

Data Index: 313193 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.4561. Min Act: -0.0000

Data Index: 779768 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3814. Min Act: -0.0001

Data Index: 510536 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3835. Min Act: -0.0000

Data Index: 367209 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3896. Min Act: -0.0001

Data Index: 1397948 (Python Code)

Max Activating Token Index: 1006

Text #16

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3855. Min Act: -0.0000

Data Index: 321950 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3135. Min Act: -0.0001

Data Index: 665686 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1653163 (Python Code)

Max Activating Token Index: 727

Text #19

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.4135. Min Act: -0.0001

Data Index: 762401 (C4 (Web Text))

Max Activating Token Index: 97