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

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

Neuron 1949 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.4329. Min Act: -0.0000

Data Index: 314212 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.4017. Min Act: -0.0000

Data Index: 258354 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1341993 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2730. Min Act: -0.0000

Data Index: 344327 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2531. Min Act: -0.0000

Data Index: 465671 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2266. Min Act: -0.0000

Data Index: 155083 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.2061. Min Act: -0.0000

Data Index: 99931 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1939. Min Act: -0.0000

Data Index: 570644 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1984. Min Act: -0.0000

Data Index: 254037 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1820. Min Act: -0.0000

Data Index: 232006 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1966. Min Act: -0.0000

Data Index: 642417 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1812. Min Act: -0.0000

Data Index: 567752 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1952. Min Act: -0.0000

Data Index: 331521 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1732. Min Act: -0.0000

Data Index: 33299 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1124980 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1857. Min Act: -0.0000

Data Index: 279749 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1771. Min Act: -0.0000

Data Index: 862912 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1882. Min Act: -0.0000

Data Index: 184940 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1815. Min Act: -0.0000

Data Index: 352717 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.4329. Min Range: -0.4329

Max Act: 0.1853. Min Act: -0.0000

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 243