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

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

Neuron 1464 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1597417 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1470130 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1580578 (Python Code)

Max Activating Token Index: 112

Text #3

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1484787 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1577383 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1515554 (Python Code)

Max Activating Token Index: 377

Text #6

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1394768 (Python Code)

Max Activating Token Index: 955

Text #7

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1414038 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1544497 (Python Code)

Max Activating Token Index: 579

Text #9

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1518542 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1509220 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1561429 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1516410 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1448456 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1491964 (Python Code)

Max Activating Token Index: 232

Text #15

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1399405 (Python Code)

Max Activating Token Index: 797

Text #16

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1587384 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1511965 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1456980 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 0.7831. Min Range: -0.7831

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1631261 (Python Code)

Max Activating Token Index: 585