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

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

Neuron 4800 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1596357 (Python Code)

Max Activating Token Index: 742

Text #1

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1197432 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1578948 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1628863 (Python Code)

Max Activating Token Index: 390

Text #4

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.3155. Min Act: -0.0000

Data Index: 1492761 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1431965 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1505789 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1422095 (Python Code)

Max Activating Token Index: 632

Text #8

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1968. Min Act: -0.0000

Data Index: 911306 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2241. Min Act: -0.0000

Data Index: 1579585 (Python Code)

Max Activating Token Index: 231

Text #10

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1360300 (Python Code)

Max Activating Token Index: 693

Text #11

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1362278 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1914. Min Act: -0.0000

Data Index: 677886 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1632527 (Python Code)

Max Activating Token Index: 713

Text #14

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1432101 (Python Code)

Max Activating Token Index: 987

Text #15

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1556126 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1587. Min Act: -0.0000

Data Index: 181696 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1629. Min Act: -0.0000

Data Index: 219977 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1474100 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.0602. Min Act: -0.0000

Data Index: 347377 (C4 (Web Text))

Max Activating Token Index: 167