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

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

Neuron 4453 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1893. Min Range: -3.1893

Max Act: 3.1893. Min Act: -0.0000

Data Index: 206028 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.7534. Min Act: -0.0000

Data Index: 928555 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.8125. Min Act: -0.0000

Data Index: 1029739 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.6327. Min Act: -0.0000

Data Index: 1053482 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.5304. Min Act: -0.0000

Data Index: 1144431 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.1944. Min Act: -0.0000

Data Index: 878186 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 3.1893. Min Range: -3.1893

Max Act: 1.9940. Min Act: -0.0000

Data Index: 977862 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.1525. Min Act: -0.0000

Data Index: 408539 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.0222. Min Act: -0.0000

Data Index: 896615 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.1025. Min Act: -0.0000

Data Index: 194311 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.1855. Min Act: -0.0000

Data Index: 949515 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.0439. Min Act: -0.0000

Data Index: 105916 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.1492. Min Act: -0.0000

Data Index: 595551 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 3.1893. Min Range: -3.1893

Max Act: 1.9012. Min Act: -0.0000

Data Index: 1329227 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.0754. Min Act: -0.0000

Data Index: 1218687 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 3.1893. Min Range: -3.1893

Max Act: 2.0238. Min Act: -0.0000

Data Index: 738105 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 3.1893. Min Range: -3.1893

Max Act: 1.9114. Min Act: -0.0000

Data Index: 416027 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.1893. Min Range: -3.1893

Max Act: 1.9119. Min Act: -0.0000

Data Index: 212917 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 3.1893. Min Range: -3.1893

Max Act: 1.9048. Min Act: -0.0000

Data Index: 455283 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 3.1893. Min Range: -3.1893

Max Act: 1.7734. Min Act: -0.0000

Data Index: 1234323 (C4 (Web Text))

Max Activating Token Index: 930