Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3920 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.7130. Min Act: -0.0001

Data Index: 1600032 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.7129. Min Act: -0.0001

Data Index: 1448190 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.6093. Min Act: -0.0001

Data Index: 1493900 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.5767. Min Act: -0.0001

Data Index: 1375716 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.5945. Min Act: -0.0001

Data Index: 1462653 (Python Code)

Max Activating Token Index: 547

Text #5

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4941. Min Act: -0.0001

Data Index: 1497491 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.5651. Min Act: -0.0001

Data Index: 1518445 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.5939. Min Act: -0.0001

Data Index: 1529638 (Python Code)

Max Activating Token Index: 739

Text #8

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.5933. Min Act: -0.0001

Data Index: 1587828 (Python Code)

Max Activating Token Index: 686

Text #9

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4574. Min Act: -0.0001

Data Index: 1558677 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4490. Min Act: -0.0001

Data Index: 1550645 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4668. Min Act: -0.0001

Data Index: 1582121 (Python Code)

Max Activating Token Index: 903

Text #12

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4354. Min Act: -0.0001

Data Index: 1439064 (Python Code)

Max Activating Token Index: 108

Text #13

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4758. Min Act: -0.0001

Data Index: 1589130 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4691. Min Act: -0.0001

Data Index: 1418310 (Python Code)

Max Activating Token Index: 915

Text #15

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4524. Min Act: -0.0001

Data Index: 1599676 (Python Code)

Max Activating Token Index: 483

Text #16

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4408. Min Act: -0.0001

Data Index: 1538688 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.4069. Min Act: -0.0001

Data Index: 1406827 (Python Code)

Max Activating Token Index: 942

Text #18

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.3396. Min Act: -0.0001

Data Index: 1576809 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 1.7130. Min Range: -1.7130

Max Act: 1.3905. Min Act: -0.0001

Data Index: 1524564 (Python Code)

Max Activating Token Index: 699