Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2868 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1115623 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2620. Min Act: -0.0001

Data Index: 795733 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1125057 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1386768 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1482457 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1446434 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1528168 (Python Code)

Max Activating Token Index: 444

Text #7

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1499926 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1556592 (Python Code)

Max Activating Token Index: 839

Text #9

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1526. Min Act: -0.0001

Data Index: 562006 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1704. Min Act: -0.0001

Data Index: 223547 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1917. Min Act: -0.0001

Data Index: 571239 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1447282 (Python Code)

Max Activating Token Index: 795

Text #13

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1505232 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1625. Min Act: -0.0001

Data Index: 564686 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1699. Min Act: -0.0001

Data Index: 118377 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1587431 (Python Code)

Max Activating Token Index: 883

Text #17

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1452. Min Act: -0.0001

Data Index: 761876 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1376883 (Python Code)

Max Activating Token Index: 240

Text #19

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1486985 (Python Code)

Max Activating Token Index: 515