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

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

Neuron 5451 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1427807 (Python Code)

Max Activating Token Index: 433

Text #1

Max Range: 1.0081. Min Range: -1.0081

Max Act: 1.0081. Min Act: -0.0000

Data Index: 1620649 (Python Code)

Max Activating Token Index: 378

Text #2

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1160032 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.8800. Min Act: -0.0000

Data Index: 39577 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.9659. Min Act: -0.0000

Data Index: 574005 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.9001. Min Act: -0.0000

Data Index: 11686 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.8587. Min Act: -0.0000

Data Index: 828546 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.8112. Min Act: -0.0000

Data Index: 929176 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1596859 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.8998. Min Act: -0.0000

Data Index: 366760 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.7738. Min Act: -0.0000

Data Index: 88773 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.8691. Min Act: -0.0000

Data Index: 440943 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.7552. Min Act: -0.0000

Data Index: 590016 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1067955 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1584335 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1105492 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.7558. Min Act: -0.0000

Data Index: 650007 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.7434. Min Act: -0.0000

Data Index: 118027 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.7419. Min Act: -0.0000

Data Index: 494214 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 1.0081. Min Range: -1.0081

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1456703 (Python Code)

Max Activating Token Index: 809