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

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

Neuron 5621 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.9885. Min Act: -0.0000

Data Index: 1607621 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.8606. Min Act: -0.0000

Data Index: 1608915 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.7082. Min Act: -0.0000

Data Index: 1511826 (Python Code)

Max Activating Token Index: 400

Text #3

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.7620. Min Act: -0.0000

Data Index: 1602090 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.7555. Min Act: -0.0000

Data Index: 1547627 (Python Code)

Max Activating Token Index: 964

Text #5

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.6645. Min Act: -0.0000

Data Index: 1420815 (Python Code)

Max Activating Token Index: 422

Text #6

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1585288 (Python Code)

Max Activating Token Index: 790

Text #7

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.5507. Min Act: -0.0000

Data Index: 1531798 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.5474. Min Act: -0.0000

Data Index: 1399445 (Python Code)

Max Activating Token Index: 696

Text #9

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1468267 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1468884 (Python Code)

Max Activating Token Index: 287

Text #11

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.5827. Min Act: -0.0000

Data Index: 1354826 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1211679 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.6344. Min Act: -0.0000

Data Index: 1579503 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1369280 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1372404 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.5357. Min Act: -0.0000

Data Index: 1527112 (Python Code)

Max Activating Token Index: 165

Text #17

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1573806 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1607128 (Python Code)

Max Activating Token Index: 354

Text #19

Max Range: 1.9885. Min Range: -1.9885

Max Act: 1.4131. Min Act: -0.0000

Data Index: 1567091 (Python Code)

Max Activating Token Index: 997