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

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

Neuron 3435 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0712. Min Act: -0.0001

Data Index: 621775 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0553. Min Act: -0.0001

Data Index: 717908 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1366942 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1484285 (Python Code)

Max Activating Token Index: 781

Text #4

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0484. Min Act: -0.0001

Data Index: 298254 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0462. Min Act: -0.0001

Data Index: 290928 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1124913 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0417. Min Act: -0.0001

Data Index: 850623 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1427293 (Python Code)

Max Activating Token Index: 329

Text #9

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0388. Min Act: -0.0001

Data Index: 363871 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1535250 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0382. Min Act: -0.0001

Data Index: 848766 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0398. Min Act: -0.0001

Data Index: 651111 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0437. Min Act: -0.0001

Data Index: 126247 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1108893 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1129868 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0391. Min Act: -0.0001

Data Index: 369133 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1464036 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0416. Min Act: -0.0000

Data Index: 1387862 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0354. Min Act: -0.0001

Data Index: 919753 (C4 (Web Text))

Max Activating Token Index: 503