Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.8764. Min Act: -0.0001

Data Index: 1582315 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.8541. Min Act: -0.0001

Data Index: 1418079 (Python Code)

Max Activating Token Index: 658

Text #2

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7060. Min Act: -0.0001

Data Index: 1598171 (Python Code)

Max Activating Token Index: 961

Text #3

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1540758 (Python Code)

Max Activating Token Index: 125

Text #4

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7060. Min Act: 0.0002

Data Index: 1501263 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6424. Min Act: -0.0001

Data Index: 1543457 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1559557 (Python Code)

Max Activating Token Index: 883

Text #7

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6564. Min Act: -0.0001

Data Index: 1601845 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6077. Min Act: -0.0001

Data Index: 1370127 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6369. Min Act: -0.0001

Data Index: 1430492 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5997. Min Act: -0.0001

Data Index: 1418842 (Python Code)

Max Activating Token Index: 185

Text #11

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5794. Min Act: 0.0000

Data Index: 1545257 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6087. Min Act: -0.0001

Data Index: 1431241 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6047. Min Act: 0.0002

Data Index: 1484789 (Python Code)

Max Activating Token Index: 413

Text #14

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5565. Min Act: -0.0001

Data Index: 1569611 (Python Code)

Max Activating Token Index: 468

Text #15

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5751. Min Act: 0.0002

Data Index: 1389860 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5556. Min Act: -0.0001

Data Index: 1641306 (Python Code)

Max Activating Token Index: 1018

Text #17

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.4944. Min Act: -0.0001

Data Index: 1507564 (Python Code)

Max Activating Token Index: 559

Text #18

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1619830 (Python Code)

Max Activating Token Index: 343

Text #19

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5065. Min Act: -0.0001

Data Index: 1449352 (Python Code)

Max Activating Token Index: 320