Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4388 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.9403. Min Act: -0.0000

Data Index: 1479454 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.6832. Min Act: -0.0000

Data Index: 1613821 (Python Code)

Max Activating Token Index: 510

Text #2

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1520122 (Python Code)

Max Activating Token Index: 309

Text #3

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5717. Min Act: -0.0000

Data Index: 1462406 (Python Code)

Max Activating Token Index: 69

Text #4

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5416. Min Act: -0.0001

Data Index: 1507662 (Python Code)

Max Activating Token Index: 523

Text #5

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5126. Min Act: -0.0000

Data Index: 1428078 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1610285 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.5381. Min Act: -0.0000

Data Index: 1524225 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1416227 (Python Code)

Max Activating Token Index: 208

Text #9

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1438232 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1497855 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1516502 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1602555 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1635905 (Python Code)

Max Activating Token Index: 59

Text #14

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1591445 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.2796. Min Act: -0.0000

Data Index: 1603565 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1463472 (Python Code)

Max Activating Token Index: 510

Text #17

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1629380 (Python Code)

Max Activating Token Index: 368

Text #18

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1582666 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 1.9403. Min Range: -1.9403

Max Act: 1.2598. Min Act: -0.0000

Data Index: 1417098 (Python Code)

Max Activating Token Index: 122