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

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

Neuron 598 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1589550 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.6185. Min Act: -0.0000

Data Index: 1503202 (Python Code)

Max Activating Token Index: 652

Text #2

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.5407. Min Act: -0.0000

Data Index: 1374643 (Python Code)

Max Activating Token Index: 107

Text #3

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.5321. Min Act: -0.0000

Data Index: 1558289 (Python Code)

Max Activating Token Index: 119

Text #4

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.5989. Min Act: -0.0000

Data Index: 1370628 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.5231. Min Act: -0.0000

Data Index: 1368639 (Python Code)

Max Activating Token Index: 435

Text #6

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.5747. Min Act: -0.0000

Data Index: 1656644 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1635394 (Python Code)

Max Activating Token Index: 987

Text #8

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4167. Min Act: -0.0000

Data Index: 1598128 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1549250 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.5183. Min Act: -0.0000

Data Index: 1490580 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4600. Min Act: -0.0000

Data Index: 1527714 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1477431 (Python Code)

Max Activating Token Index: 1005

Text #13

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4486. Min Act: -0.0000

Data Index: 1445484 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4042. Min Act: -0.0000

Data Index: 1609990 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4964. Min Act: -0.0000

Data Index: 1610060 (Python Code)

Max Activating Token Index: 51

Text #16

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4787. Min Act: -0.0000

Data Index: 1604272 (Python Code)

Max Activating Token Index: 819

Text #17

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1478607 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.4365. Min Act: -0.0000

Data Index: 1521129 (Python Code)

Max Activating Token Index: 796

Text #19

Max Range: 1.6185. Min Range: -1.6185

Max Act: 1.3804. Min Act: -0.0000

Data Index: 1415577 (Python Code)

Max Activating Token Index: 44