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

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

Neuron 1591 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: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0003

Data Index: 706663 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0473. Min Act: -0.0003

Data Index: 79322 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1485249 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0490. Min Act: -0.0003

Data Index: 676712 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0488. Min Act: -0.0003

Data Index: 833539 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1506297 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0467. Min Act: -0.0003

Data Index: 75090 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1637777 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0458. Min Act: -0.0003

Data Index: 178237 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1476604 (Python Code)

Max Activating Token Index: 683

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0426. Min Act: -0.0003

Data Index: 47041 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1412360 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0409. Min Act: -0.0003

Data Index: 383799 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1510639 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0401. Min Act: -0.0003

Data Index: 456663 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0423. Min Act: -0.0003

Data Index: 624208 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1288941 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1595589 (Python Code)

Max Activating Token Index: 835

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1017400 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1653636 (Python Code)

Max Activating Token Index: 997