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

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

Neuron 1132 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0002

Data Index: 212526 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1244751 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0516. Min Act: -0.0002

Data Index: 25746 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0486. Min Act: -0.0002

Data Index: 865065 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0455. Min Act: -0.0002

Data Index: 747229 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0470. Min Act: -0.0002

Data Index: 489622 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0431. Min Act: -0.0002

Data Index: 820154 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1156916 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0449. Min Act: -0.0002

Data Index: 250587 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0426. Min Act: -0.0002

Data Index: 735156 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0421. Min Act: -0.0002

Data Index: 582411 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0419. Min Act: -0.0002

Data Index: 470322 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0412. Min Act: -0.0002

Data Index: 638174 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1236508 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1226680 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0410. Min Act: -0.0002

Data Index: 913342 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1289028 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1147551 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1354396 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0396. Min Act: -0.0002

Data Index: 923721 (C4 (Web Text))

Max Activating Token Index: 917