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

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

Neuron 2636 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0722. Min Act: -0.0004

Data Index: 1311040 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0696. Min Act: -0.0004

Data Index: 560715 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0702. Min Act: -0.0004

Data Index: 101149 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0004

Data Index: 943134 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0655. Min Act: -0.0004

Data Index: 83783 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0734. Min Act: -0.0004

Data Index: 526883 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0649. Min Act: -0.0004

Data Index: 447797 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0655. Min Act: -0.0004

Data Index: 381841 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0650. Min Act: -0.0004

Data Index: 533705 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0577. Min Act: -0.0004

Data Index: 326047 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0644. Min Act: -0.0004

Data Index: 1157850 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0618. Min Act: -0.0004

Data Index: 950358 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0641. Min Act: -0.0004

Data Index: 545345 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0641. Min Act: -0.0004

Data Index: 499080 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0639. Min Act: -0.0004

Data Index: 999652 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0617. Min Act: -0.0004

Data Index: 364724 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0665. Min Act: -0.0004

Data Index: 820402 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0665. Min Act: -0.0004

Data Index: 787670 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0658. Min Act: -0.0004

Data Index: 616004 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0606. Min Act: -0.0004

Data Index: 288066 (C4 (Web Text))

Max Activating Token Index: 286