Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1614 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6795. Min Act: -0.0001

Data Index: 1369319 (Python Code)

Max Activating Token Index: 78

Text #1

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6280. Min Act: -0.0001

Data Index: 926496 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6270. Min Act: -0.0001

Data Index: 1377452 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6201. Min Act: -0.0001

Data Index: 1475184 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5642. Min Act: -0.0001

Data Index: 1502342 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5400. Min Act: -0.0001

Data Index: 1456313 (Python Code)

Max Activating Token Index: 136

Text #6

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5593. Min Act: -0.0001

Data Index: 1651977 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5484. Min Act: -0.0001

Data Index: 1461444 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5303. Min Act: -0.0001

Data Index: 1517552 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5570. Min Act: -0.0001

Data Index: 1050693 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5188. Min Act: -0.0001

Data Index: 133205 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1454575 (Python Code)

Max Activating Token Index: 429

Text #12

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5130. Min Act: -0.0001

Data Index: 1645082 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4756. Min Act: -0.0001

Data Index: 1406151 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4998. Min Act: -0.0001

Data Index: 1498912 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5000. Min Act: -0.0001

Data Index: 1385885 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4762. Min Act: -0.0001

Data Index: 1386466 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4721. Min Act: -0.0001

Data Index: 1608795 (Python Code)

Max Activating Token Index: 142

Text #18

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5058. Min Act: -0.0001

Data Index: 1635822 (Python Code)

Max Activating Token Index: 706

Text #19

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4802. Min Act: -0.0001

Data Index: 1513365 (Python Code)

Max Activating Token Index: 54