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

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

Neuron 3387 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3737. Min Range: -7.3737

Max Act: 7.3737. Min Act: -0.0001

Data Index: 361548 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 7.3737. Min Range: -7.3737

Max Act: 7.1380. Min Act: -0.0001

Data Index: 48490 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.4750. Min Act: -0.0001

Data Index: 959717 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.6227. Min Act: -0.0001

Data Index: 333470 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.2982. Min Act: -0.0001

Data Index: 1157550 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.2567. Min Act: -0.0001

Data Index: 366099 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.3852. Min Act: -0.0001

Data Index: 490618 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.5357. Min Act: -0.0001

Data Index: 40860 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.5040. Min Act: -0.0001

Data Index: 409609 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.4887. Min Act: -0.0001

Data Index: 563444 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.4657. Min Act: -0.0001

Data Index: 990965 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.2470. Min Act: -0.0001

Data Index: 1310399 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 7.3737. Min Range: -7.3737

Max Act: 5.8405. Min Act: -0.0001

Data Index: 523074 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.1800. Min Act: -0.0001

Data Index: 1290867 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 7.3737. Min Range: -7.3737

Max Act: 5.9723. Min Act: -0.0001

Data Index: 383566 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.1172. Min Act: -0.0001

Data Index: 824252 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.2903. Min Act: -0.0001

Data Index: 1061204 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.0811. Min Act: -0.0001

Data Index: 541508 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 7.3737. Min Range: -7.3737

Max Act: 5.5295. Min Act: -0.0001

Data Index: 1201965 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 7.3737. Min Range: -7.3737

Max Act: 6.1721. Min Act: -0.0001

Data Index: 1326294 (C4 (Web Text))

Max Activating Token Index: 716