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

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

Neuron 3861 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6807. Min Act: -0.0000

Data Index: 542082 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5704. Min Act: -0.0000

Data Index: 408559 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5845. Min Act: -0.0000

Data Index: 258782 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1043383 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1261261 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6109. Min Act: -0.0000

Data Index: 465703 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5418. Min Act: -0.0000

Data Index: 905485 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5954. Min Act: -0.0000

Data Index: 904085 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5229. Min Act: -0.0000

Data Index: 977468 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5294. Min Act: -0.0000

Data Index: 653935 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5387. Min Act: -0.0000

Data Index: 762972 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4588. Min Act: -0.0000

Data Index: 222372 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1296662 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4702. Min Act: -0.0000

Data Index: 571641 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4793. Min Act: -0.0000

Data Index: 248184 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4913. Min Act: -0.0000

Data Index: 551379 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4594. Min Act: -0.0000

Data Index: 892581 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4907. Min Act: -0.0000

Data Index: 132968 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1302544 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5028. Min Act: -0.0000

Data Index: 560765 (C4 (Web Text))

Max Activating Token Index: 768