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

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

Neuron 4356 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.8150. Min Act: -0.0001

Data Index: 1445811 (Python Code)

Max Activating Token Index: 557

Text #1

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5756. Min Act: -0.0001

Data Index: 1404142 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5554. Min Act: -0.0001

Data Index: 1550366 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5836. Min Act: -0.0001

Data Index: 1360020 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.6109. Min Act: -0.0001

Data Index: 1435708 (Python Code)

Max Activating Token Index: 471

Text #5

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.6621. Min Act: -0.0001

Data Index: 1647786 (Python Code)

Max Activating Token Index: 785

Text #6

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5690. Min Act: -0.0001

Data Index: 1474841 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5670. Min Act: -0.0001

Data Index: 1486204 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5903. Min Act: -0.0001

Data Index: 1489706 (Python Code)

Max Activating Token Index: 429

Text #9

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.4101. Min Act: -0.0001

Data Index: 1555529 (Python Code)

Max Activating Token Index: 756

Text #10

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5047. Min Act: -0.0001

Data Index: 1645729 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5719. Min Act: -0.0001

Data Index: 1492637 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5938. Min Act: -0.0000

Data Index: 1618571 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5061. Min Act: -0.0001

Data Index: 1636229 (Python Code)

Max Activating Token Index: 1021

Text #14

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.3650. Min Act: -0.0001

Data Index: 1422987 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.4732. Min Act: -0.0001

Data Index: 1496129 (Python Code)

Max Activating Token Index: 966

Text #16

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.5118. Min Act: -0.0001

Data Index: 1368796 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.4243. Min Act: -0.0000

Data Index: 1409175 (Python Code)

Max Activating Token Index: 473

Text #18

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.4962. Min Act: -0.0001

Data Index: 1493894 (Python Code)

Max Activating Token Index: 1020

Text #19

Max Range: 1.8150. Min Range: -1.8150

Max Act: 1.6288. Min Act: -0.0000

Data Index: 1389756 (Python Code)

Max Activating Token Index: 592