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

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

Neuron 5043 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: 1.6577. Min Range: -1.6577

Max Act: 1.6577. Min Act: -0.0001

Data Index: 675753 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3328. Min Act: -0.0001

Data Index: 1004553 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3616. Min Act: -0.0001

Data Index: 1326577 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2879. Min Act: -0.0001

Data Index: 528028 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2750. Min Act: -0.0001

Data Index: 814549 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2581. Min Act: -0.0001

Data Index: 459924 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2933. Min Act: -0.0001

Data Index: 800584 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2976. Min Act: -0.0001

Data Index: 547766 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0103. Min Act: -0.0001

Data Index: 114821 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.1045. Min Act: -0.0001

Data Index: 919682 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0294. Min Act: -0.0001

Data Index: 412029 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0980. Min Act: -0.0001

Data Index: 1082494 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0479. Min Act: -0.0001

Data Index: 769213 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 1.6577. Min Range: -1.6577

Max Act: 0.9863. Min Act: -0.0001

Data Index: 272770 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0782. Min Act: -0.0001

Data Index: 1112791 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0733. Min Act: -0.0001

Data Index: 203597 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0941. Min Act: -0.0001

Data Index: 794246 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0184. Min Act: -0.0001

Data Index: 316872 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0424. Min Act: -0.0001

Data Index: 514903 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.0770. Min Act: -0.0001

Data Index: 1346338 (C4 (Web Text))

Max Activating Token Index: 932