Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2717 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1928. Min Range: -2.1928

Max Act: 2.1928. Min Act: -0.0000

Data Index: 482242 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.9333. Min Act: -0.0000

Data Index: 396091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.8099. Min Act: -0.0000

Data Index: 1025401 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 2.1928. Min Range: -2.1928

Max Act: 2.0445. Min Act: -0.0000

Data Index: 114189 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.5604. Min Act: -0.0000

Data Index: 263559 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.6952. Min Act: -0.0000

Data Index: 1192567 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.7788. Min Act: -0.0000

Data Index: 218894 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.6525. Min Act: -0.0000

Data Index: 61588 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.6463. Min Act: -0.0000

Data Index: 955709 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.5609. Min Act: -0.0000

Data Index: 872443 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.7358. Min Act: -0.0000

Data Index: 1103717 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.6071. Min Act: -0.0000

Data Index: 77542 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.6045. Min Act: -0.0000

Data Index: 881148 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.6776. Min Act: -0.0000

Data Index: 862719 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.5820. Min Act: -0.0000

Data Index: 452626 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.6630. Min Act: -0.0000

Data Index: 792321 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.6461. Min Act: -0.0000

Data Index: 40181 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.5346. Min Act: -0.0000

Data Index: 307540 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.4617. Min Act: -0.0000

Data Index: 111341 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 2.1928. Min Range: -2.1928

Max Act: 1.4942. Min Act: -0.0000

Data Index: 258177 (C4 (Web Text))

Max Activating Token Index: 364