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

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

Neuron 3738 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.8838. Min Act: -0.0000

Data Index: 541445 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.8767. Min Act: -0.0000

Data Index: 698780 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1298882 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6326. Min Act: -0.0000

Data Index: 649828 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6467. Min Act: -0.0000

Data Index: 938429 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6705. Min Act: -0.0000

Data Index: 891949 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6125. Min Act: -0.0000

Data Index: 22739 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6436. Min Act: -0.0000

Data Index: 526389 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1017175 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5899. Min Act: -0.0000

Data Index: 809464 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1145815 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6015. Min Act: -0.0000

Data Index: 650912 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1008751 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5962. Min Act: -0.0000

Data Index: 212871 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6347. Min Act: -0.0000

Data Index: 68370 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6333. Min Act: -0.0000

Data Index: 405534 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5958. Min Act: -0.0000

Data Index: 89550 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6147. Min Act: -0.0000

Data Index: 710429 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6063. Min Act: -0.0000

Data Index: 896831 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6038. Min Act: -0.0000

Data Index: 271280 (C4 (Web Text))

Max Activating Token Index: 692