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

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

Neuron 1576 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.6100. Min Act: -0.0002

Data Index: 1635741 (Python Code)

Max Activating Token Index: 916

Text #1

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5034. Min Act: -0.0002

Data Index: 1491564 (Python Code)

Max Activating Token Index: 78

Text #2

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5081. Min Act: -0.0002

Data Index: 729378 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5449. Min Act: -0.0002

Data Index: 324858 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5341. Min Act: -0.0002

Data Index: 1061789 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4869. Min Act: -0.0002

Data Index: 1459137 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5079. Min Act: -0.0002

Data Index: 1413990 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5029. Min Act: -0.0002

Data Index: 1491395 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5349. Min Act: -0.0002

Data Index: 244390 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5499. Min Act: -0.0002

Data Index: 988714 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5290. Min Act: -0.0002

Data Index: 1566367 (Python Code)

Max Activating Token Index: 717

Text #11

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5126. Min Act: -0.0002

Data Index: 87454 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5126. Min Act: -0.0002

Data Index: 51260 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5126. Min Act: -0.0002

Data Index: 1034975 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5432. Min Act: -0.0002

Data Index: 700607 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5091. Min Act: -0.0002

Data Index: 440012 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4612. Min Act: -0.0002

Data Index: 512973 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5120. Min Act: -0.0002

Data Index: 1624536 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5353. Min Act: -0.0002

Data Index: 395542 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5256. Min Act: -0.0002

Data Index: 1181374 (C4 (Web Text))

Max Activating Token Index: 565