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

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

Neuron 3742 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: 0.5940. Min Range: -0.5940

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1600742 (Python Code)

Max Activating Token Index: 706

Text #1

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1517095 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1403399 (Python Code)

Max Activating Token Index: 996

Text #3

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1462117 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1484679 (Python Code)

Max Activating Token Index: 375

Text #5

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5356. Min Act: -0.0001

Data Index: 1465282 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5086. Min Act: -0.0001

Data Index: 1559977 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5181. Min Act: -0.0001

Data Index: 1438645 (Python Code)

Max Activating Token Index: 71

Text #8

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1456792 (Python Code)

Max Activating Token Index: 800

Text #9

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4856. Min Act: -0.0001

Data Index: 1540320 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5430. Min Act: -0.0001

Data Index: 1414223 (Python Code)

Max Activating Token Index: 42

Text #11

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1429379 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5430. Min Act: -0.0001

Data Index: 1626031 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1446738 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1509508 (Python Code)

Max Activating Token Index: 807

Text #15

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1440492 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4813. Min Act: -0.0001

Data Index: 1583344 (Python Code)

Max Activating Token Index: 225

Text #17

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1548271 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1550267 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5330. Min Act: -0.0001

Data Index: 1563250 (Python Code)

Max Activating Token Index: 205