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

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

Neuron 906 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: 0.2329. Min Range: -0.2329

Max Act: 0.2329. Min Act: -0.0000

Data Index: 980700 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.2192. Min Act: 0.0000

Data Index: 631972 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.2106. Min Act: 0.0000

Data Index: 78739 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1991. Min Act: -0.0000

Data Index: 996595 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1929. Min Act: -0.0000

Data Index: 860592 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1921. Min Act: -0.0000

Data Index: 495812 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1267694 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1928. Min Act: 0.0000

Data Index: 136759 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1855. Min Act: -0.0000

Data Index: 321605 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1812. Min Act: -0.0000

Data Index: 458784 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1816. Min Act: -0.0000

Data Index: 522669 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1814. Min Act: -0.0000

Data Index: 863153 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1797. Min Act: -0.0000

Data Index: 258989 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1757. Min Act: -0.0000

Data Index: 629496 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1076856 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1737. Min Act: -0.0000

Data Index: 969113 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1742. Min Act: -0.0000

Data Index: 254894 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1689. Min Act: -0.0000

Data Index: 30064 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1725. Min Act: -0.0000

Data Index: 733888 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.2329. Min Range: -0.2329

Max Act: 0.1651. Min Act: -0.0000

Data Index: 484847 (C4 (Web Text))

Max Activating Token Index: 437