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

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

Neuron 2249 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.1782. Min Range: -9.1782

Max Act: 9.1782. Min Act: -0.0000

Data Index: 226050 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 9.1782. Min Range: -9.1782

Max Act: 8.8066. Min Act: -0.0000

Data Index: 701835 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 9.1782. Min Range: -9.1782

Max Act: 8.3534. Min Act: -0.0000

Data Index: 598306 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 9.1782. Min Range: -9.1782

Max Act: 8.0508. Min Act: -0.0000

Data Index: 1220514 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 9.1782. Min Range: -9.1782

Max Act: 7.5193. Min Act: -0.0000

Data Index: 190079 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 9.1782. Min Range: -9.1782

Max Act: 7.4443. Min Act: -0.0000

Data Index: 46794 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 9.1782. Min Range: -9.1782

Max Act: 7.1347. Min Act: -0.0000

Data Index: 1162738 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 9.1782. Min Range: -9.1782

Max Act: 7.3695. Min Act: -0.0000

Data Index: 580405 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 9.1782. Min Range: -9.1782

Max Act: 7.1526. Min Act: -0.0000

Data Index: 1275891 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 9.1782. Min Range: -9.1782

Max Act: 7.0715. Min Act: -0.0000

Data Index: 29334 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 9.1782. Min Range: -9.1782

Max Act: 7.0698. Min Act: -0.0000

Data Index: 203716 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.6102. Min Act: -0.0000

Data Index: 801580 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.3461. Min Act: -0.0000

Data Index: 982606 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.3500. Min Act: -0.0000

Data Index: 490676 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.5290. Min Act: -0.0000

Data Index: 47335 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.4924. Min Act: -0.0000

Data Index: 682647 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.4645. Min Act: -0.0000

Data Index: 899149 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.5646. Min Act: -0.0000

Data Index: 994248 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.4047. Min Act: -0.0000

Data Index: 14410 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 9.1782. Min Range: -9.1782

Max Act: 6.3761. Min Act: -0.0000

Data Index: 1332756 (C4 (Web Text))

Max Activating Token Index: 521