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

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

Neuron 1706 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.1273. Min Act: -0.0000

Data Index: 270727 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0651. Min Act: -0.0000

Data Index: 216778 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0617. Min Act: -0.0000

Data Index: 381378 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9525. Min Act: -0.0000

Data Index: 807666 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8739. Min Act: -0.0000

Data Index: 941661 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8695. Min Act: -0.0000

Data Index: 685745 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8440. Min Act: -0.0000

Data Index: 710448 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.7739. Min Act: -0.0000

Data Index: 449412 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.7331. Min Act: -0.0000

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6967. Min Act: -0.0000

Data Index: 816473 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1184325 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6482. Min Act: -0.0000

Data Index: 16383 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6749. Min Act: -0.0000

Data Index: 501050 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1011103 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6251. Min Act: -0.0000

Data Index: 572409 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1011135 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6516. Min Act: -0.0000

Data Index: 497759 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6341. Min Act: -0.0000

Data Index: 674911 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6624. Min Act: -0.0000

Data Index: 133113 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.6324. Min Act: -0.0000

Data Index: 655536 (C4 (Web Text))

Max Activating Token Index: 503