Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 479 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2186. Min Act: -0.0001

Data Index: 18946 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2029. Min Act: -0.0001

Data Index: 300987 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1990. Min Act: -0.0001

Data Index: 759334 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2039. Min Act: -0.0001

Data Index: 675827 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1862. Min Act: -0.0001

Data Index: 475391 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1320994 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1904. Min Act: -0.0001

Data Index: 642579 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1958. Min Act: -0.0001

Data Index: 511932 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1852. Min Act: -0.0001

Data Index: 989101 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1778. Min Act: -0.0001

Data Index: 216701 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1834. Min Act: -0.0001

Data Index: 351269 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1772. Min Act: -0.0001

Data Index: 186552 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1444991 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1810. Min Act: -0.0001

Data Index: 154989 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1799. Min Act: -0.0001

Data Index: 195059 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1793. Min Act: -0.0001

Data Index: 558247 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1787. Min Act: -0.0001

Data Index: 254680 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1563250 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1792. Min Act: -0.0001

Data Index: 776276 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1716. Min Act: -0.0001

Data Index: 1538832 (Python Code)

Max Activating Token Index: 338