Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3350 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1434735 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3252. Min Act: -0.0001

Data Index: 1605508 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1503777 (Python Code)

Max Activating Token Index: 569

Text #3

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1395980 (Python Code)

Max Activating Token Index: 504

Text #4

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3226. Min Act: -0.0001

Data Index: 1647309 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1449729 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1492361 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1617148 (Python Code)

Max Activating Token Index: 954

Text #8

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2960. Min Act: -0.0001

Data Index: 1372543 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1496696 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1468439 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2805. Min Act: -0.0001

Data Index: 1587134 (Python Code)

Max Activating Token Index: 564

Text #12

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1598293 (Python Code)

Max Activating Token Index: 626

Text #13

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1423330 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2809. Min Act: -0.0001

Data Index: 1526434 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2680. Min Act: -0.0001

Data Index: 1500708 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1414870 (Python Code)

Max Activating Token Index: 449

Text #17

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1471904 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1497267 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.2688. Min Act: -0.0001

Data Index: 1422248 (Python Code)

Max Activating Token Index: 273