Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3234 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1367044 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6396. Min Act: -0.0000

Data Index: 628481 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6083. Min Act: -0.0000

Data Index: 421860 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1214116 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5603. Min Act: -0.0000

Data Index: 133098 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5348. Min Act: -0.0000

Data Index: 171710 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1648827 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5149. Min Act: -0.0000

Data Index: 818114 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5267. Min Act: -0.0000

Data Index: 200907 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5092. Min Act: -0.0000

Data Index: 421661 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1488626 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4829. Min Act: -0.0000

Data Index: 707879 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4797. Min Act: -0.0000

Data Index: 672662 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1306120 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1336960 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1415134 (Python Code)

Max Activating Token Index: 659

Text #16

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1391794 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4578. Min Act: -0.0000

Data Index: 649637 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4676. Min Act: -0.0000

Data Index: 733397 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1615429 (Python Code)

Max Activating Token Index: 363