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

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

Neuron 4870 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1381076 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1407193 (Python Code)

Max Activating Token Index: 724

Text #2

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1431609 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1380263 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1564316 (Python Code)

Max Activating Token Index: 274

Text #5

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1630398 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1452225 (Python Code)

Max Activating Token Index: 996

Text #7

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1478864 (Python Code)

Max Activating Token Index: 433

Text #8

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1512245 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1436645 (Python Code)

Max Activating Token Index: 817

Text #10

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1373844 (Python Code)

Max Activating Token Index: 759

Text #11

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1542. Min Act: -0.0000

Data Index: 720400 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1397783 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1544333 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1627601 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1651032 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1413300 (Python Code)

Max Activating Token Index: 866

Text #17

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1603. Min Act: -0.0000

Data Index: 124439 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1396206 (Python Code)

Max Activating Token Index: 462

Text #19

Max Range: 0.1961. Min Range: -0.1961

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1655023 (Python Code)

Max Activating Token Index: 718