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

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

Neuron 4727 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: 0.3585. Min Range: -0.3585

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1275005 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3585. Min Act: -0.0000

Data Index: 284669 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3229. Min Act: -0.0000

Data Index: 229080 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3390. Min Act: -0.0000

Data Index: 10525 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1072693 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3220. Min Act: -0.0000

Data Index: 820776 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3485. Min Act: -0.0000

Data Index: 841077 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1328701 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1293164 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1266106 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2692. Min Act: -0.0000

Data Index: 294741 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1274076 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2768. Min Act: -0.0000

Data Index: 515488 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2555. Min Act: -0.0000

Data Index: 848109 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2454. Min Act: -0.0000

Data Index: 574469 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2510. Min Act: -0.0000

Data Index: 857509 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1302000 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1025554 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2693. Min Act: -0.0000

Data Index: 803602 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1195682 (C4 (Web Text))

Max Activating Token Index: 270