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

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

Neuron 5780 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: 0.3003. Min Range: -0.3003

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1620374 (Python Code)

Max Activating Token Index: 776

Text #1

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1499501 (Python Code)

Max Activating Token Index: 530

Text #2

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1413272 (Python Code)

Max Activating Token Index: 787

Text #3

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1441968 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2134. Min Act: -0.0000

Data Index: 845519 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1386730 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2098. Min Act: -0.0000

Data Index: 975260 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2134. Min Act: -0.0000

Data Index: 1638113 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1392259 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1378881 (Python Code)

Max Activating Token Index: 819

Text #10

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1407445 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1519876 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1637042 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1577679 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1578773 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1546593 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1396958 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1566124 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1585730 (Python Code)

Max Activating Token Index: 490

Text #19

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1524762 (Python Code)

Max Activating Token Index: 461