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

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

Neuron 860 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1405075 (Python Code)

Max Activating Token Index: 991

Text #1

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1490005 (Python Code)

Max Activating Token Index: 643

Text #2

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1648177 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1598646 (Python Code)

Max Activating Token Index: 828

Text #4

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1541122 (Python Code)

Max Activating Token Index: 929

Text #5

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1461470 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1656745 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1407945 (Python Code)

Max Activating Token Index: 1003

Text #8

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1593674 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1387495 (Python Code)

Max Activating Token Index: 980

Text #10

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5124. Min Act: -0.0000

Data Index: 782022 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1525845 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1595078 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1531487 (Python Code)

Max Activating Token Index: 979

Text #14

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1469696 (Python Code)

Max Activating Token Index: 807

Text #15

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1556685 (Python Code)

Max Activating Token Index: 998

Text #16

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1472249 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1554318 (Python Code)

Max Activating Token Index: 686

Text #18

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1454863 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4773. Min Act: -0.0000

Data Index: 691900 (C4 (Web Text))

Max Activating Token Index: 824