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

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

Neuron 4674 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1200638 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.8709. Min Act: -0.0000

Data Index: 923328 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1122600 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.8976. Min Act: -0.0000

Data Index: 882656 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.8112. Min Act: -0.0000

Data Index: 623315 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1355004 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1182597 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7684. Min Act: -0.0000

Data Index: 725660 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1042415 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1157375 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.8159. Min Act: -0.0000

Data Index: 840077 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7704. Min Act: -0.0000

Data Index: 116695 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7751. Min Act: -0.0000

Data Index: 31633 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1195315 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7371. Min Act: -0.0000

Data Index: 927588 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7261. Min Act: -0.0000

Data Index: 835389 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1233926 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1176088 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1272686 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.9341. Min Range: -0.9341

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1114410 (C4 (Web Text))

Max Activating Token Index: 404