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

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

Neuron 1852 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.8414. Min Act: -0.0001

Data Index: 402453 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7973. Min Act: -0.0000

Data Index: 381372 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7792. Min Act: -0.0000

Data Index: 568492 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7476. Min Act: -0.0000

Data Index: 219600 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6942. Min Act: -0.0001

Data Index: 1554521 (Python Code)

Max Activating Token Index: 817

Text #5

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6953. Min Act: -0.0001

Data Index: 907431 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6767. Min Act: -0.0001

Data Index: 978017 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6409. Min Act: -0.0000

Data Index: 233300 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6760. Min Act: -0.0000

Data Index: 322148 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1322364 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1035294 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6219. Min Act: -0.0000

Data Index: 83984 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6051. Min Act: -0.0001

Data Index: 1170341 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6003. Min Act: -0.0000

Data Index: 515785 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5909. Min Act: -0.0001

Data Index: 1362101 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5755. Min Act: -0.0001

Data Index: 163629 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5914. Min Act: -0.0001

Data Index: 1517086 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1127628 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6261. Min Act: -0.0001

Data Index: 701803 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 316