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

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

Neuron 1866 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: 0.6822. Min Range: -0.6822

Max Act: 0.6822. Min Act: -0.0001

Data Index: 158324 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.6316. Min Act: -0.0001

Data Index: 718924 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1344968 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5895. Min Act: -0.0001

Data Index: 645471 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5898. Min Act: -0.0001

Data Index: 1287095 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5665. Min Act: -0.0001

Data Index: 1117408 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5453. Min Act: -0.0001

Data Index: 998143 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5626. Min Act: -0.0001

Data Index: 1285773 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5774. Min Act: -0.0001

Data Index: 792487 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5220. Min Act: -0.0001

Data Index: 413703 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5737. Min Act: -0.0001

Data Index: 1310250 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5375. Min Act: -0.0001

Data Index: 227174 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5842. Min Act: -0.0001

Data Index: 836994 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5650. Min Act: -0.0001

Data Index: 974651 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5664. Min Act: -0.0001

Data Index: 1210571 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1151083 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5586. Min Act: -0.0001

Data Index: 353957 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5729. Min Act: -0.0001

Data Index: 718743 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5414. Min Act: -0.0001

Data Index: 701018 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.6822. Min Range: -0.6822

Max Act: 0.5572. Min Act: -0.0001

Data Index: 560074 (C4 (Web Text))

Max Activating Token Index: 679