Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5266 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2715. Min Range: -5.2715

Max Act: 5.2715. Min Act: -0.0000

Data Index: 715412 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 5.2715. Min Range: -5.2715

Max Act: 5.1878. Min Act: -0.0000

Data Index: 1204836 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 5.2715. Min Range: -5.2715

Max Act: 4.8161. Min Act: -0.0000

Data Index: 389543 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 5.2715. Min Range: -5.2715

Max Act: 4.3971. Min Act: -0.0000

Data Index: 470597 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.6730. Min Act: -0.0000

Data Index: 265348 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.9681. Min Act: -0.0000

Data Index: 831890 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.9426. Min Act: -0.0000

Data Index: 656267 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.5361. Min Act: -0.0000

Data Index: 1225927 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.7018. Min Act: -0.0000

Data Index: 1488256 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.7059. Min Act: -0.0000

Data Index: 2562 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.4917. Min Act: -0.0000

Data Index: 578866 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.1450. Min Act: -0.0000

Data Index: 884293 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.2576. Min Act: -0.0000

Data Index: 764355 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.2419. Min Act: -0.0000

Data Index: 1585097 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.2339. Min Act: -0.0000

Data Index: 1106196 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 5.2715. Min Range: -5.2715

Max Act: 2.7735. Min Act: -0.0000

Data Index: 1470672 (Python Code)

Max Activating Token Index: 932

Text #16

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.2103. Min Act: -0.0000

Data Index: 1569264 (Python Code)

Max Activating Token Index: 702

Text #17

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.3105. Min Act: -0.0000

Data Index: 1501744 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.3776. Min Act: -0.0000

Data Index: 210655 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 5.2715. Min Range: -5.2715

Max Act: 3.2351. Min Act: -0.0000

Data Index: 81420 (C4 (Web Text))

Max Activating Token Index: 704