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

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

Neuron 817 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: 0.0807. Min Range: -0.0807

Max Act: 0.0799. Min Act: -0.0000

Data Index: 488387 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0795. Min Act: -0.0000

Data Index: 176007 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0789. Min Act: -0.0000

Data Index: 761471 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0000

Data Index: 673628 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0771. Min Act: -0.0000

Data Index: 125991 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1208749 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0726. Min Act: -0.0000

Data Index: 369035 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1465144 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0735. Min Act: -0.0000

Data Index: 940027 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1025463 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0712. Min Act: -0.0000

Data Index: 662642 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0714. Min Act: -0.0000

Data Index: 267177 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0697. Min Act: -0.0000

Data Index: 928377 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0662. Min Act: -0.0000

Data Index: 607328 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0661. Min Act: -0.0000

Data Index: 8974 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0708. Min Act: -0.0000

Data Index: 1209581 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0659. Min Act: -0.0000

Data Index: 846820 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1148028 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0653. Min Act: -0.0000

Data Index: 297526 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0647. Min Act: -0.0000

Data Index: 582260 (C4 (Web Text))

Max Activating Token Index: 360