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

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

Neuron 3185 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: 1.1941. Min Range: -1.1941

Max Act: 1.1941. Min Act: -0.0001

Data Index: 1388710 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.1032. Min Act: -0.0001

Data Index: 1565005 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.0851. Min Act: -0.0001

Data Index: 1431447 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.0498. Min Act: -0.0001

Data Index: 1614444 (Python Code)

Max Activating Token Index: 18

Text #4

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.1547. Min Act: -0.0001

Data Index: 1470902 (Python Code)

Max Activating Token Index: 168

Text #5

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.0431. Min Act: -0.0001

Data Index: 1656067 (Python Code)

Max Activating Token Index: 245

Text #6

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.0022. Min Act: -0.0001

Data Index: 1427169 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 1.1941. Min Range: -1.1941

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1632856 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9504. Min Act: -0.0001

Data Index: 1625429 (Python Code)

Max Activating Token Index: 103

Text #9

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9717. Min Act: -0.0001

Data Index: 1583872 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9817. Min Act: -0.0001

Data Index: 1572242 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9423. Min Act: -0.0001

Data Index: 1576334 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9090. Min Act: -0.0001

Data Index: 1610421 (Python Code)

Max Activating Token Index: 131

Text #13

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8999. Min Act: -0.0001

Data Index: 1376612 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9709. Min Act: -0.0001

Data Index: 1416054 (Python Code)

Max Activating Token Index: 785

Text #15

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8923. Min Act: -0.0001

Data Index: 1436155 (Python Code)

Max Activating Token Index: 910

Text #16

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9024. Min Act: -0.0001

Data Index: 1466391 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9249. Min Act: -0.0001

Data Index: 1551207 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.9353. Min Act: -0.0001

Data Index: 1460365 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 1.1941. Min Range: -1.1941

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1617040 (Python Code)

Max Activating Token Index: 774