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

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

Neuron 4600 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1485063 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1640060 (Python Code)

Max Activating Token Index: 873

Text #2

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1525562 (Python Code)

Max Activating Token Index: 465

Text #3

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1522200 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1393022 (Python Code)

Max Activating Token Index: 1009

Text #5

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1385827 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2283. Min Act: -0.0000

Data Index: 368049 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2105. Min Act: -0.0000

Data Index: 689690 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1628475 (Python Code)

Max Activating Token Index: 552

Text #9

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1606105 (Python Code)

Max Activating Token Index: 735

Text #10

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2021. Min Act: -0.0000

Data Index: 295729 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1944. Min Act: -0.0000

Data Index: 175089 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1647550 (Python Code)

Max Activating Token Index: 377

Text #13

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1898. Min Act: -0.0000

Data Index: 294257 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1598521 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1985. Min Act: -0.0000

Data Index: 221072 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1868. Min Act: -0.0000

Data Index: 504436 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1591553 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1521011 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1910. Min Act: -0.0000

Data Index: 458510 (C4 (Web Text))

Max Activating Token Index: 205