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

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

Neuron 888 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0655. Min Range: -1.0655

Max Act: 1.0655. Min Act: -0.0000

Data Index: 629171 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8865. Min Act: -0.0000

Data Index: 369434 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8489. Min Act: -0.0000

Data Index: 186158 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1222175 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7884. Min Act: -0.0000

Data Index: 926404 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7741. Min Act: -0.0000

Data Index: 882458 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1128077 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1613617 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.7322. Min Act: -0.0000

Data Index: 649611 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1408687 (Python Code)

Max Activating Token Index: 424

Text #10

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6818. Min Act: -0.0000

Data Index: 462921 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1023108 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1391481 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1656873 (Python Code)

Max Activating Token Index: 625

Text #14

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6409. Min Act: -0.0000

Data Index: 766481 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6112. Min Act: -0.0000

Data Index: 372480 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1634296 (Python Code)

Max Activating Token Index: 734

Text #17

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1652060 (Python Code)

Max Activating Token Index: 616

Text #18

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6130. Min Act: -0.0000

Data Index: 993617 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.0655. Min Range: -1.0655

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1483568 (Python Code)

Max Activating Token Index: 880