Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 732 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1879. Min Act: -0.0003

Data Index: 546306 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1773. Min Act: -0.0002

Data Index: 799042 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1795. Min Act: -0.0003

Data Index: 153585 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1851. Min Act: -0.0003

Data Index: 312013 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1602. Min Act: -0.0003

Data Index: 657750 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1626. Min Act: -0.0003

Data Index: 1050214 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1466. Min Act: -0.0003

Data Index: 1276996 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1542. Min Act: -0.0003

Data Index: 503150 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1504. Min Act: -0.0003

Data Index: 372695 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1408. Min Act: -0.0003

Data Index: 97007 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1521. Min Act: -0.0003

Data Index: 985181 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1452. Min Act: -0.0003

Data Index: 400396 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1487. Min Act: -0.0003

Data Index: 287882 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1430. Min Act: -0.0003

Data Index: 1239099 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1476. Min Act: -0.0003

Data Index: 1208049 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1430. Min Act: -0.0003

Data Index: 573831 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1292. Min Act: -0.0003

Data Index: 467360 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1536. Min Act: -0.0003

Data Index: 987154 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1328. Min Act: -0.0003

Data Index: 1085306 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1533. Min Act: -0.0003

Data Index: 162041 (C4 (Web Text))

Max Activating Token Index: 54