Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 49 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2435. Min Act: -0.0002

Data Index: 1390003 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2097. Min Act: -0.0002

Data Index: 1502873 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2289. Min Act: -0.0002

Data Index: 1645939 (Python Code)

Max Activating Token Index: 548

Text #3

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2171. Min Act: -0.0002

Data Index: 1606360 (Python Code)

Max Activating Token Index: 746

Text #4

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2122. Min Act: -0.0002

Data Index: 1642970 (Python Code)

Max Activating Token Index: 623

Text #5

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1492579 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2137. Min Act: -0.0002

Data Index: 1419711 (Python Code)

Max Activating Token Index: 510

Text #7

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1978. Min Act: -0.0002

Data Index: 649794 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2016. Min Act: -0.0002

Data Index: 1418406 (Python Code)

Max Activating Token Index: 860

Text #9

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1932. Min Act: -0.0002

Data Index: 1411815 (Python Code)

Max Activating Token Index: 836

Text #10

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1458333 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1986. Min Act: -0.0002

Data Index: 1361939 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1945. Min Act: -0.0002

Data Index: 1539714 (Python Code)

Max Activating Token Index: 532

Text #13

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1918. Min Act: -0.0002

Data Index: 1393144 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1934. Min Act: -0.0002

Data Index: 1480781 (Python Code)

Max Activating Token Index: 393

Text #15

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2039. Min Act: -0.0002

Data Index: 1640320 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1973. Min Act: -0.0002

Data Index: 1466298 (Python Code)

Max Activating Token Index: 699

Text #17

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1380694 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1887. Min Act: -0.0002

Data Index: 1375505 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1866. Min Act: -0.0002

Data Index: 1513612 (Python Code)

Max Activating Token Index: 850