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

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

Neuron 2411 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4622. Min Act: -0.0001

Data Index: 180700 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4116. Min Act: -0.0001

Data Index: 172238 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3334. Min Act: -0.0001

Data Index: 759738 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3360. Min Act: -0.0001

Data Index: 351712 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3146. Min Act: -0.0001

Data Index: 298840 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3082. Min Act: -0.0001

Data Index: 86993 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3260. Min Act: -0.0001

Data Index: 922039 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2984. Min Act: -0.0001

Data Index: 417472 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2962. Min Act: -0.0001

Data Index: 840848 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2845. Min Act: -0.0001

Data Index: 1599698 (Python Code)

Max Activating Token Index: 828

Text #10

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2939. Min Act: -0.0001

Data Index: 700374 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3002. Min Act: -0.0001

Data Index: 1603856 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2949. Min Act: -0.0001

Data Index: 671052 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3306. Min Act: -0.0001

Data Index: 997045 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2835. Min Act: -0.0001

Data Index: 706721 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2855. Min Act: -0.0001

Data Index: 755426 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3036. Min Act: -0.0001

Data Index: 1180421 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2910. Min Act: -0.0001

Data Index: 310942 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.2828. Min Act: -0.0001

Data Index: 361644 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3028. Min Act: -0.0001

Data Index: 32702 (C4 (Web Text))

Max Activating Token Index: 512