Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2364 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.8219. Min Act: -0.0000

Data Index: 786179 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7616. Min Act: -0.0000

Data Index: 971811 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1218734 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6909. Min Act: -0.0000

Data Index: 584789 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1302227 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6639. Min Act: -0.0000

Data Index: 205712 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.6378. Min Act: -0.0000

Data Index: 278336 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5827. Min Act: -0.0000

Data Index: 833295 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1205386 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5657. Min Act: -0.0000

Data Index: 198900 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1112514 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5721. Min Act: -0.0000

Data Index: 237087 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5475. Min Act: -0.0000

Data Index: 746355 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5658. Min Act: -0.0000

Data Index: 770796 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5816. Min Act: -0.0000

Data Index: 115950 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5439. Min Act: -0.0000

Data Index: 334758 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1162788 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5570. Min Act: -0.0000

Data Index: 80759 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5566. Min Act: -0.0000

Data Index: 596101 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.8219. Min Range: -0.8219

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1024466 (C4 (Web Text))

Max Activating Token Index: 959