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

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

Neuron 4084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7656. Min Act: -0.0000

Data Index: 442561 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6916. Min Act: -0.0001

Data Index: 264392 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1324104 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7223. Min Act: -0.0001

Data Index: 1278577 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7197. Min Act: -0.0001

Data Index: 1600875 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7072. Min Act: -0.0001

Data Index: 330193 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.7083. Min Act: -0.0001

Data Index: 476340 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6951. Min Act: -0.0000

Data Index: 491546 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6926. Min Act: -0.0001

Data Index: 567827 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6896. Min Act: -0.0001

Data Index: 592512 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6472. Min Act: -0.0001

Data Index: 513711 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6566. Min Act: -0.0001

Data Index: 1113881 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6676. Min Act: -0.0001

Data Index: 386327 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1654293 (Python Code)

Max Activating Token Index: 868

Text #14

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6794. Min Act: -0.0000

Data Index: 715666 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6577. Min Act: -0.0001

Data Index: 1570910 (Python Code)

Max Activating Token Index: 991

Text #16

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6299. Min Act: -0.0000

Data Index: 546 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6697. Min Act: -0.0000

Data Index: 981820 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6291. Min Act: -0.0000

Data Index: 410583 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.7656. Min Range: -0.7656

Max Act: 0.6882. Min Act: -0.0001

Data Index: 335658 (C4 (Web Text))

Max Activating Token Index: 987