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

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

Neuron 2721 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1034625 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0047. Min Act: -0.0003

Data Index: 601340 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0003

Data Index: 891595 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0047. Min Act: -0.0003

Data Index: 334843 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0047. Min Act: -0.0003

Data Index: 46120 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0003

Data Index: 562573 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0003

Data Index: 828768 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0003

Data Index: 8350 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 979211 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 885288 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 927250 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 420366 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1276555 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 609837 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1154633 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 447837 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1031477 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 629056 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1158732 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1000434 (C4 (Web Text))

Max Activating Token Index: 774