Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3434 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2338. Min Act: -0.0000

Data Index: 209667 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2119. Min Act: -0.0000

Data Index: 938184 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1297101 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1158821 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1895. Min Act: -0.0000

Data Index: 838714 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1837. Min Act: -0.0001

Data Index: 1271491 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1857. Min Act: -0.0000

Data Index: 197819 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1188713 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1658. Min Act: -0.0000

Data Index: 138429 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1675. Min Act: -0.0000

Data Index: 445698 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1647. Min Act: -0.0001

Data Index: 551737 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1650. Min Act: -0.0000

Data Index: 397012 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1593. Min Act: -0.0001

Data Index: 607256 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1118592 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1540. Min Act: -0.0000

Data Index: 805066 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1507. Min Act: -0.0000

Data Index: 45490 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1213802 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1217764 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1542. Min Act: -0.0001

Data Index: 196761 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1675. Min Act: -0.0001

Data Index: 446646 (C4 (Web Text))

Max Activating Token Index: 827