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

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

Neuron 1282 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: 0.7607. Min Range: -0.7607

Max Act: 0.7607. Min Act: -0.0002

Data Index: 107783 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6776. Min Act: -0.0002

Data Index: 340595 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6706. Min Act: -0.0002

Data Index: 291839 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6377. Min Act: -0.0002

Data Index: 1344658 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5706. Min Act: -0.0002

Data Index: 1306126 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5689. Min Act: -0.0002

Data Index: 1208472 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5875. Min Act: -0.0002

Data Index: 1193686 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6048. Min Act: -0.0002

Data Index: 1143817 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5450. Min Act: -0.0002

Data Index: 1350690 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5972. Min Act: -0.0002

Data Index: 778582 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5748. Min Act: -0.0002

Data Index: 631872 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5532. Min Act: -0.0002

Data Index: 644047 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5055. Min Act: -0.0002

Data Index: 552570 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5217. Min Act: -0.0002

Data Index: 175710 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5193. Min Act: -0.0002

Data Index: 772775 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4519. Min Act: -0.0002

Data Index: 832978 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4824. Min Act: -0.0001

Data Index: 1230542 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4898. Min Act: -0.0002

Data Index: 746165 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4845. Min Act: -0.0002

Data Index: 278168 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4842. Min Act: -0.0002

Data Index: 326390 (C4 (Web Text))

Max Activating Token Index: 646