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

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

Neuron 4067 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1639721 (Python Code)

Max Activating Token Index: 720

Text #1

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6849. Min Act: -0.0000

Data Index: 173865 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6938. Min Act: -0.0000

Data Index: 665441 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.7130. Min Act: -0.0000

Data Index: 900707 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6939. Min Act: -0.0000

Data Index: 726402 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1525750 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1467459 (Python Code)

Max Activating Token Index: 116

Text #7

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1074998 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6268. Min Act: -0.0000

Data Index: 947737 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1469892 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1525721 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1540414 (Python Code)

Max Activating Token Index: 860

Text #12

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1196073 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6089. Min Act: -0.0000

Data Index: 876559 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1438000 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1372860 (Python Code)

Max Activating Token Index: 282

Text #16

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1430403 (Python Code)

Max Activating Token Index: 862

Text #17

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5796. Min Act: -0.0000

Data Index: 777340 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1627642 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1229332 (C4 (Web Text))

Max Activating Token Index: 242