Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2432 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1196608 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3268. Min Act: -0.0001

Data Index: 632866 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1622084 (Python Code)

Max Activating Token Index: 650

Text #3

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3222. Min Act: -0.0000

Data Index: 663264 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2925. Min Act: -0.0000

Data Index: 641754 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2791. Min Act: 0.0000

Data Index: 1384624 (Python Code)

Max Activating Token Index: 538

Text #6

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2684. Min Act: 0.0003

Data Index: 731251 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2781. Min Act: 0.0001

Data Index: 1160429 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1459705 (Python Code)

Max Activating Token Index: 556

Text #9

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1494236 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1583949 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1174027 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2773. Min Act: 0.0000

Data Index: 713471 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2778. Min Act: -0.0000

Data Index: 684477 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1618910 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1401643 (Python Code)

Max Activating Token Index: 299

Text #16

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1591279 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1594763 (Python Code)

Max Activating Token Index: 395

Text #18

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2597. Min Act: -0.0000

Data Index: 911766 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2605. Min Act: -0.0000

Data Index: 327386 (C4 (Web Text))

Max Activating Token Index: 324