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

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

Neuron 477 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8511. Min Range: -7.8511

Max Act: 7.8511. Min Act: -0.0000

Data Index: 1107849 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 7.8511. Min Range: -7.8511

Max Act: 7.6747. Min Act: -0.0000

Data Index: 41013 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 7.8511. Min Range: -7.8511

Max Act: 7.1456. Min Act: -0.0000

Data Index: 66823 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 7.8511. Min Range: -7.8511

Max Act: 6.5163. Min Act: -0.0000

Data Index: 1195669 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 7.8511. Min Range: -7.8511

Max Act: 6.6734. Min Act: -0.0000

Data Index: 252627 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 7.8511. Min Range: -7.8511

Max Act: 6.0820. Min Act: -0.0000

Data Index: 1126067 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 7.8511. Min Range: -7.8511

Max Act: 6.4340. Min Act: -0.0000

Data Index: 1158519 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.8467. Min Act: -0.0000

Data Index: 324686 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 7.8511. Min Range: -7.8511

Max Act: 6.4844. Min Act: -0.0000

Data Index: 1050824 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.9634. Min Act: -0.0000

Data Index: 926619 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.6002. Min Act: -0.0000

Data Index: 471037 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 7.8511. Min Range: -7.8511

Max Act: 6.2259. Min Act: -0.0000

Data Index: 155808 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.8909. Min Act: -0.0000

Data Index: 117738 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 7.8511. Min Range: -7.8511

Max Act: 6.0101. Min Act: -0.0000

Data Index: 765130 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.9779. Min Act: -0.0000

Data Index: 984282 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.5972. Min Act: -0.0000

Data Index: 851080 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.9300. Min Act: -0.0000

Data Index: 617760 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.6904. Min Act: -0.0000

Data Index: 955908 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.8772. Min Act: -0.0000

Data Index: 1011116 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 7.8511. Min Range: -7.8511

Max Act: 5.8698. Min Act: -0.0000

Data Index: 846612 (C4 (Web Text))

Max Activating Token Index: 205