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

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

Neuron 5703 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1333024 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1955. Min Act: -0.0000

Data Index: 54811 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1393353 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1644821 (Python Code)

Max Activating Token Index: 1002

Text #4

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1542234 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1444050 (Python Code)

Max Activating Token Index: 675

Text #6

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1565975 (Python Code)

Max Activating Token Index: 889

Text #7

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1737. Min Act: -0.0000

Data Index: 573283 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1608. Min Act: -0.0000

Data Index: 855383 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1389659 (Python Code)

Max Activating Token Index: 448

Text #10

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1251909 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1454602 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1430. Min Act: -0.0000

Data Index: 337324 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1503698 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1459. Min Act: -0.0000

Data Index: 444884 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1421694 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1465539 (Python Code)

Max Activating Token Index: 340

Text #17

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1343. Min Act: -0.0000

Data Index: 523033 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1572642 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1386. Min Act: -0.0000

Data Index: 760485 (C4 (Web Text))

Max Activating Token Index: 693