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

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

Neuron 1511 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1370297 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1419071 (Python Code)

Max Activating Token Index: 383

Text #2

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1459066 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1370859 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1520810 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1456891 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1404846 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1446150 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1539354 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1642352 (Python Code)

Max Activating Token Index: 281

Text #10

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1362532 (Python Code)

Max Activating Token Index: 822

Text #11

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1625826 (Python Code)

Max Activating Token Index: 944

Text #12

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1558071 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1381594 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1426493 (Python Code)

Max Activating Token Index: 525

Text #15

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1454074 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1645551 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1401842 (Python Code)

Max Activating Token Index: 624

Text #18

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1374728 (Python Code)

Max Activating Token Index: 657

Text #19

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1605968 (Python Code)

Max Activating Token Index: 28