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

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

Neuron 4606 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0155. Min Range: -1.0155

Max Act: 1.0150. Min Act: -0.0000

Data Index: 966551 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.0155. Min Range: -1.0155

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1029138 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1093756 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7658. Min Act: -0.0000

Data Index: 349049 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8696. Min Act: -0.0000

Data Index: 27192 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8512. Min Act: -0.0001

Data Index: 119452 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8571. Min Act: -0.0000

Data Index: 673520 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8094. Min Act: -0.0000

Data Index: 258768 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1322787 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1282295 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7921. Min Act: -0.0000

Data Index: 525867 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1091716 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7785. Min Act: -0.0000

Data Index: 386609 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7753. Min Act: -0.0000

Data Index: 937492 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1081280 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7521. Min Act: -0.0000

Data Index: 239481 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7491. Min Act: -0.0000

Data Index: 8386 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7145. Min Act: -0.0000

Data Index: 589782 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.7350. Min Act: -0.0000

Data Index: 959302 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 1.0155. Min Range: -1.0155

Max Act: 0.8061. Min Act: -0.0000

Data Index: 481974 (C4 (Web Text))

Max Activating Token Index: 833