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

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

Neuron 4798 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3511. Min Act: -0.0002

Data Index: 1112293 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3508. Min Act: -0.0002

Data Index: 605512 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3157. Min Act: -0.0002

Data Index: 131207 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3370. Min Act: -0.0002

Data Index: 792050 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3373. Min Act: -0.0002

Data Index: 755169 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3206. Min Act: -0.0002

Data Index: 572529 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3068. Min Act: -0.0002

Data Index: 940375 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2831. Min Act: -0.0002

Data Index: 990527 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3137. Min Act: -0.0002

Data Index: 911485 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2864. Min Act: -0.0002

Data Index: 655140 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2673. Min Act: -0.0002

Data Index: 1481550 (Python Code)

Max Activating Token Index: 255

Text #11

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3323. Min Act: -0.0002

Data Index: 345720 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3058. Min Act: -0.0002

Data Index: 272453 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3016. Min Act: -0.0002

Data Index: 837963 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.3110. Min Act: -0.0002

Data Index: 1008049 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2970. Min Act: -0.0002

Data Index: 464268 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2995. Min Act: -0.0002

Data Index: 188751 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2969. Min Act: -0.0002

Data Index: 1220942 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2838. Min Act: -0.0002

Data Index: 648586 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.3511. Min Range: -0.3511

Max Act: 0.2813. Min Act: -0.0002

Data Index: 1294546 (C4 (Web Text))

Max Activating Token Index: 992