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

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

Neuron 296 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: 0.4903. Min Range: -0.4903

Max Act: 0.4903. Min Act: -0.0000

Data Index: 148059 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4401. Min Act: -0.0000

Data Index: 706752 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3846. Min Act: 0.0000

Data Index: 1447891 (Python Code)

Max Activating Token Index: 139

Text #3

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3617. Min Act: 0.0000

Data Index: 1060153 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1502306 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1397942 (Python Code)

Max Activating Token Index: 512

Text #6

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3245. Min Act: -0.0000

Data Index: 568284 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3236. Min Act: -0.0000

Data Index: 359203 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1577441 (Python Code)

Max Activating Token Index: 157

Text #9

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3007. Min Act: -0.0000

Data Index: 462273 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3080. Min Act: -0.0000

Data Index: 411288 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1533530 (Python Code)

Max Activating Token Index: 429

Text #12

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2816. Min Act: -0.0000

Data Index: 669074 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2887. Min Act: -0.0000

Data Index: 7663 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1621006 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1561183 (Python Code)

Max Activating Token Index: 867

Text #16

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1408370 (Python Code)

Max Activating Token Index: 913

Text #17

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2601. Min Act: -0.0000

Data Index: 625678 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1453851 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.2400. Min Act: 0.0001

Data Index: 252864 (C4 (Web Text))

Max Activating Token Index: 444