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

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

Neuron 2097 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.8928. Min Act: -0.0001

Data Index: 326755 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1130095 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.8543. Min Act: -0.0001

Data Index: 904942 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.8209. Min Act: -0.0001

Data Index: 842716 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.7432. Min Act: -0.0001

Data Index: 953117 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6567. Min Act: -0.0001

Data Index: 1314386 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6455. Min Act: -0.0001

Data Index: 13803 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6853. Min Act: -0.0001

Data Index: 630042 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6544. Min Act: -0.0001

Data Index: 1039898 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6524. Min Act: -0.0001

Data Index: 193777 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6332. Min Act: -0.0001

Data Index: 988574 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6261. Min Act: -0.0001

Data Index: 419094 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.5930. Min Act: -0.0001

Data Index: 243484 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6128. Min Act: -0.0001

Data Index: 621010 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1276147 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6112. Min Act: -0.0001

Data Index: 16527 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6350. Min Act: -0.0001

Data Index: 557622 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.5891. Min Act: -0.0001

Data Index: 760797 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6750. Min Act: -0.0001

Data Index: 1096704 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.8928. Min Range: -0.8928

Max Act: 0.6022. Min Act: -0.0001

Data Index: 974694 (C4 (Web Text))

Max Activating Token Index: 100