Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1832 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0761. Min Act: -0.0003

Data Index: 1622678 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1442892 (Python Code)

Max Activating Token Index: 888

Text #2

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1457060 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1436877 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1536405 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1644899 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1516218 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1430251 (Python Code)

Max Activating Token Index: 911

Text #8

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1524586 (Python Code)

Max Activating Token Index: 769

Text #9

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1502885 (Python Code)

Max Activating Token Index: 798

Text #10

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1493312 (Python Code)

Max Activating Token Index: 996

Text #11

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1397604 (Python Code)

Max Activating Token Index: 849

Text #12

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1652907 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1404126 (Python Code)

Max Activating Token Index: 998

Text #14

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1654864 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1626210 (Python Code)

Max Activating Token Index: 976

Text #16

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1513801 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1596800 (Python Code)

Max Activating Token Index: 692

Text #18

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1541657 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0413. Min Act: -0.0003

Data Index: 1375001 (Python Code)

Max Activating Token Index: 4