Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1705 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1606525 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1589029 (Python Code)

Max Activating Token Index: 478

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1561408 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0461. Min Act: -0.0003

Data Index: 150761 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1460048 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1629027 (Python Code)

Max Activating Token Index: 761

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1363636 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0429. Min Act: -0.0003

Data Index: 194867 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1100129 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1580373 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1622992 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1572954 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1639249 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1487831 (Python Code)

Max Activating Token Index: 875

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1263643 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0395. Min Act: -0.0003

Data Index: 157389 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1516899 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0382. Min Act: -0.0003

Data Index: 207660 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1526679 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1393760 (Python Code)

Max Activating Token Index: 688