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

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

Neuron 3376 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.9676. Min Act: -0.0000

Data Index: 693305 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.8018. Min Act: -0.0000

Data Index: 157727 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.7251. Min Act: -0.0000

Data Index: 199415 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.3863. Min Act: -0.0000

Data Index: 552738 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.1815. Min Act: -0.0000

Data Index: 584550 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.3290. Min Act: -0.0000

Data Index: 10287 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.2108. Min Act: -0.0000

Data Index: 425642 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.1983. Min Act: -0.0000

Data Index: 1048307 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.0722. Min Act: -0.0000

Data Index: 1160627 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.6973. Min Act: -0.0000

Data Index: 354599 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.9676. Min Range: -2.9676

Max Act: 2.2310. Min Act: -0.0000

Data Index: 551309 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.9718. Min Act: -0.0000

Data Index: 239032 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.9837. Min Act: -0.0000

Data Index: 932781 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.8983. Min Act: -0.0000

Data Index: 945566 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.8560. Min Act: -0.0000

Data Index: 617884 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.8265. Min Act: -0.0000

Data Index: 162639 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.7324. Min Act: -0.0000

Data Index: 882348 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.8578. Min Act: -0.0000

Data Index: 565019 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.7080. Min Act: -0.0000

Data Index: 972197 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 2.9676. Min Range: -2.9676

Max Act: 1.7980. Min Act: -0.0000

Data Index: 103144 (C4 (Web Text))

Max Activating Token Index: 457