Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1991 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0735. Min Act: -0.0002

Data Index: 860452 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0730. Min Act: -0.0001

Data Index: 894583 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1298776 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0696. Min Act: -0.0001

Data Index: 123997 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0719. Min Act: -0.0002

Data Index: 999358 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0673. Min Act: -0.0001

Data Index: 43674 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1125487 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0706. Min Act: -0.0001

Data Index: 431628 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1232685 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0729. Min Act: -0.0002

Data Index: 883624 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0722. Min Act: -0.0002

Data Index: 474563 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0001

Data Index: 849931 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0689. Min Act: -0.0001

Data Index: 562106 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0705. Min Act: -0.0001

Data Index: 720306 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0677. Min Act: -0.0001

Data Index: 672002 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1229010 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0656. Min Act: -0.0001

Data Index: 939004 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0672. Min Act: -0.0001

Data Index: 442015 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1263456 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0672. Min Act: -0.0001

Data Index: 485876 (C4 (Web Text))

Max Activating Token Index: 139