Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 514 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0002

Data Index: 761469 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1059738 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0899. Min Act: -0.0002

Data Index: 315980 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0896. Min Act: -0.0001

Data Index: 490562 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1052667 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0834. Min Act: -0.0002

Data Index: 210268 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0834. Min Act: -0.0002

Data Index: 909191 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0815. Min Act: -0.0002

Data Index: 214619 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1323549 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0797. Min Act: -0.0002

Data Index: 198018 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0742. Min Act: -0.0002

Data Index: 286575 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0761. Min Act: -0.0002

Data Index: 24921 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1302823 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0758. Min Act: -0.0002

Data Index: 434243 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0743. Min Act: -0.0002

Data Index: 816304 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0756. Min Act: -0.0002

Data Index: 707865 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0739. Min Act: -0.0002

Data Index: 859687 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1013062 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0742. Min Act: -0.0002

Data Index: 802021 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0731. Min Act: -0.0002

Data Index: 852740 (C4 (Web Text))

Max Activating Token Index: 572