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

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

Neuron 3699 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1362485 (Python Code)

Max Activating Token Index: 66

Text #1

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1434773 (Python Code)

Max Activating Token Index: 620

Text #2

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1631986 (Python Code)

Max Activating Token Index: 185

Text #3

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1601112 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1642607 (Python Code)

Max Activating Token Index: 1001

Text #5

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1437852 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1440146 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1408980 (Python Code)

Max Activating Token Index: 108

Text #8

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1393002 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1563691 (Python Code)

Max Activating Token Index: 309

Text #10

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1522277 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1441998 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1425770 (Python Code)

Max Activating Token Index: 647

Text #13

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1526230 (Python Code)

Max Activating Token Index: 35

Text #14

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5785. Min Act: -0.0000

Data Index: 829321 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1549675 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1602337 (Python Code)

Max Activating Token Index: 1007

Text #17

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1459325 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5898. Min Act: -0.0000

Data Index: 241069 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1601217 (Python Code)

Max Activating Token Index: 616