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

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

Neuron 1588 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: 0.2976. Min Range: -0.2976

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1460855 (Python Code)

Max Activating Token Index: 274

Text #1

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1452771 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1368523 (Python Code)

Max Activating Token Index: 603

Text #3

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1406723 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1557213 (Python Code)

Max Activating Token Index: 299

Text #5

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1633196 (Python Code)

Max Activating Token Index: 916

Text #6

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2314. Min Act: -0.0000

Data Index: 667401 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1506407 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1500405 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2143. Min Act: -0.0000

Data Index: 367848 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1556499 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1360263 (Python Code)

Max Activating Token Index: 148

Text #12

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2039. Min Act: -0.0000

Data Index: 282343 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2053. Min Act: -0.0000

Data Index: 546561 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1215328 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1387107 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1640155 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1420113 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1521225 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1609776 (Python Code)

Max Activating Token Index: 825