Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5397 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6629. Min Range: -4.6629

Max Act: 4.6629. Min Act: -0.0000

Data Index: 1194535 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 4.6629. Min Range: -4.6629

Max Act: 4.5037. Min Act: -0.0000

Data Index: 807949 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 4.6629. Min Range: -4.6629

Max Act: 4.2512. Min Act: -0.0000

Data Index: 283938 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.8784. Min Act: -0.0000

Data Index: 561356 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 4.6629. Min Range: -4.6629

Max Act: 4.1642. Min Act: -0.0000

Data Index: 93512 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.9209. Min Act: 0.0000

Data Index: 601866 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.9891. Min Act: -0.0000

Data Index: 922851 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.8500. Min Act: -0.0000

Data Index: 874355 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 4.6629. Min Range: -4.6629

Max Act: 4.0063. Min Act: -0.0000

Data Index: 960259 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.7578. Min Act: -0.0000

Data Index: 1229528 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.7072. Min Act: -0.0000

Data Index: 860265 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.5441. Min Act: -0.0000

Data Index: 226609 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.3718. Min Act: -0.0000

Data Index: 140830 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.5066. Min Act: -0.0000

Data Index: 1040940 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.4971. Min Act: -0.0000

Data Index: 1340249 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.4928. Min Act: -0.0000

Data Index: 1302844 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.5935. Min Act: -0.0000

Data Index: 1112832 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.2364. Min Act: -0.0000

Data Index: 1285736 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.1647. Min Act: -0.0000

Data Index: 1278318 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 4.6629. Min Range: -4.6629

Max Act: 3.3816. Min Act: -0.0000

Data Index: 142004 (C4 (Web Text))

Max Activating Token Index: 33