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

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

Neuron 5117 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: 1.5614. Min Range: -1.5614

Max Act: 1.5348. Min Act: -0.0000

Data Index: 735557 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.5614. Min Act: -0.0000

Data Index: 24798 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.2501. Min Act: -0.0000

Data Index: 30414 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.2192. Min Act: -0.0000

Data Index: 614037 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.2835. Min Act: -0.0000

Data Index: 792862 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1348012 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1535. Min Act: -0.0000

Data Index: 751589 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.2219. Min Act: -0.0000

Data Index: 337708 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1415. Min Act: -0.0000

Data Index: 437613 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1222. Min Act: -0.0000

Data Index: 801437 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1106. Min Act: -0.0000

Data Index: 298020 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0579. Min Act: -0.0000

Data Index: 882514 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0576. Min Act: -0.0000

Data Index: 185462 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0512. Min Act: -0.0000

Data Index: 994110 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0477. Min Act: -0.0000

Data Index: 527595 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0409. Min Act: -0.0000

Data Index: 793942 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 1.5614. Min Range: -1.5614

Max Act: 0.9791. Min Act: -0.0000

Data Index: 544802 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0335. Min Act: -0.0000

Data Index: 361352 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1091. Min Act: -0.0000

Data Index: 284517 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0308. Min Act: -0.0000

Data Index: 907270 (C4 (Web Text))

Max Activating Token Index: 70