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

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

Neuron 2685 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1553113 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1530429 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0140. Min Act: -0.0002

Data Index: 679912 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0138. Min Act: -0.0002

Data Index: 900109 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1645590 (Python Code)

Max Activating Token Index: 756

Text #5

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1085716 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1543587 (Python Code)

Max Activating Token Index: 408

Text #7

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0129. Min Act: -0.0002

Data Index: 655297 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1115729 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0126. Min Act: -0.0002

Data Index: 866815 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0129. Min Act: -0.0002

Data Index: 604895 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1644891 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0128. Min Act: -0.0002

Data Index: 633083 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1014714 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0125. Min Act: -0.0002

Data Index: 918201 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1568923 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1118602 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0127. Min Act: -0.0002

Data Index: 233400 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0126. Min Act: -0.0002

Data Index: 747580 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0126. Min Act: -0.0002

Data Index: 834752 (C4 (Web Text))

Max Activating Token Index: 524