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

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

Neuron 1875 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.7698. Min Act: -0.0000

Data Index: 399382 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.1400. Min Act: -0.0000

Data Index: 375746 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.1391. Min Act: -0.0000

Data Index: 295245 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1325080 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.1441. Min Act: -0.0000

Data Index: 12959 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.0403. Min Act: -0.0000

Data Index: 591416 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.9735. Min Act: -0.0000

Data Index: 678673 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1117088 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1188344 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.9693. Min Act: -0.0000

Data Index: 350983 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.7698. Min Range: -1.7698

Max Act: 1.0060. Min Act: -0.0000

Data Index: 860645 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.9525. Min Act: -0.0000

Data Index: 833997 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.9017. Min Act: -0.0000

Data Index: 741730 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.9320. Min Act: -0.0000

Data Index: 927090 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.9082. Min Act: -0.0000

Data Index: 613320 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.8824. Min Act: -0.0000

Data Index: 731159 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1107006 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.8980. Min Act: -0.0000

Data Index: 193654 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.8872. Min Act: -0.0000

Data Index: 90578 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 1.7698. Min Range: -1.7698

Max Act: 0.9033. Min Act: -0.0000

Data Index: 872094 (C4 (Web Text))

Max Activating Token Index: 116