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

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

Neuron 4383 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: 0.2125. Min Range: -0.2125

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1415994 (Python Code)

Max Activating Token Index: 526

Text #1

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.2125. Min Act: -0.0000

Data Index: 350873 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.2119. Min Act: -0.0000

Data Index: 594917 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1676. Min Act: -0.0000

Data Index: 524458 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1987. Min Act: -0.0000

Data Index: 993937 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1441333 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1932. Min Act: -0.0000

Data Index: 945965 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1053369 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1232412 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1895. Min Act: -0.0000

Data Index: 100213 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1008563 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1468874 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1498913 (Python Code)

Max Activating Token Index: 543

Text #13

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1696. Min Act: -0.0000

Data Index: 608622 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1620145 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1093059 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1783. Min Act: -0.0000

Data Index: 687589 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1601. Min Act: -0.0000

Data Index: 76824 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1667. Min Act: -0.0000

Data Index: 296517 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1512. Min Act: -0.0000

Data Index: 736247 (C4 (Web Text))

Max Activating Token Index: 758