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

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

Neuron 5992 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: 4.4504. Min Range: -4.4504

Max Act: 4.4504. Min Act: -0.0000

Data Index: 906053 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 4.4504. Min Range: -4.4504

Max Act: 4.2924. Min Act: -0.0000

Data Index: 1034484 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.8166. Min Act: -0.0000

Data Index: 92928 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.3656. Min Act: -0.0000

Data Index: 84288 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.3135. Min Act: -0.0000

Data Index: 923499 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.3308. Min Act: -0.0000

Data Index: 126708 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 4.4504. Min Range: -4.4504

Max Act: 2.9657. Min Act: -0.0000

Data Index: 1529295 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.2297. Min Act: -0.0000

Data Index: 1627091 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.0614. Min Act: -0.0000

Data Index: 1397820 (Python Code)

Max Activating Token Index: 220

Text #9

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.3218. Min Act: -0.0000

Data Index: 1498891 (Python Code)

Max Activating Token Index: 788

Text #10

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.2011. Min Act: -0.0000

Data Index: 102108 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 4.4504. Min Range: -4.4504

Max Act: 2.8829. Min Act: -0.0000

Data Index: 1389373 (Python Code)

Max Activating Token Index: 170

Text #12

Max Range: 4.4504. Min Range: -4.4504

Max Act: 2.8731. Min Act: -0.0000

Data Index: 1557660 (Python Code)

Max Activating Token Index: 946

Text #13

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.3091. Min Act: -0.0000

Data Index: 606892 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.2754. Min Act: -0.0000

Data Index: 1376866 (Python Code)

Max Activating Token Index: 334

Text #15

Max Range: 4.4504. Min Range: -4.4504

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1619943 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.1014. Min Act: -0.0000

Data Index: 87402 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.2727. Min Act: -0.0000

Data Index: 1220003 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 4.4504. Min Range: -4.4504

Max Act: 3.2392. Min Act: -0.0000

Data Index: 628680 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 4.4504. Min Range: -4.4504

Max Act: 2.9602. Min Act: -0.0000

Data Index: 1505469 (Python Code)

Max Activating Token Index: 136