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

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

Neuron 1218 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2826. Min Act: -0.0004

Data Index: 1535735 (Python Code)

Max Activating Token Index: 703

Text #1

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2437. Min Act: -0.0004

Data Index: 1563018 (Python Code)

Max Activating Token Index: 530

Text #2

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2696. Min Act: -0.0004

Data Index: 1431851 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2780. Min Act: -0.0004

Data Index: 1559661 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2288. Min Act: -0.0004

Data Index: 1587287 (Python Code)

Max Activating Token Index: 837

Text #5

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2450. Min Act: -0.0004

Data Index: 1449039 (Python Code)

Max Activating Token Index: 357

Text #6

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2636. Min Act: -0.0004

Data Index: 1507129 (Python Code)

Max Activating Token Index: 493

Text #7

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2444. Min Act: -0.0004

Data Index: 1474118 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2519. Min Act: -0.0004

Data Index: 1408869 (Python Code)

Max Activating Token Index: 708

Text #9

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2733. Min Act: -0.0004

Data Index: 1571949 (Python Code)

Max Activating Token Index: 591

Text #10

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2683. Min Act: -0.0004

Data Index: 1535750 (Python Code)

Max Activating Token Index: 533

Text #11

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2596. Min Act: -0.0004

Data Index: 1381536 (Python Code)

Max Activating Token Index: 539

Text #12

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2511. Min Act: -0.0004

Data Index: 1615281 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2394. Min Act: -0.0004

Data Index: 1500095 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2547. Min Act: -0.0004

Data Index: 1427249 (Python Code)

Max Activating Token Index: 621

Text #15

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2449. Min Act: -0.0004

Data Index: 1525331 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2287. Min Act: -0.0004

Data Index: 1499235 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2443. Min Act: -0.0004

Data Index: 1374868 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2620. Min Act: -0.0004

Data Index: 1584408 (Python Code)

Max Activating Token Index: 780

Text #19

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2436. Min Act: -0.0004

Data Index: 1478780 (Python Code)

Max Activating Token Index: 641