Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 321 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0004

Data Index: 783116 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0432. Min Act: -0.0004

Data Index: 402936 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0406. Min Act: -0.0004

Data Index: 203054 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0406. Min Act: -0.0004

Data Index: 532483 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0392. Min Act: -0.0004

Data Index: 984947 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0408. Min Act: -0.0004

Data Index: 61424 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0385. Min Act: -0.0004

Data Index: 862215 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0386. Min Act: -0.0004

Data Index: 521901 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0408. Min Act: -0.0004

Data Index: 1271740 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0388. Min Act: -0.0004

Data Index: 934013 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0402. Min Act: -0.0004

Data Index: 876269 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0392. Min Act: -0.0004

Data Index: 166026 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0378. Min Act: -0.0004

Data Index: 1140241 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0343. Min Act: -0.0004

Data Index: 973559 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0377. Min Act: -0.0004

Data Index: 853902 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0375. Min Act: -0.0004

Data Index: 1240103 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0388. Min Act: -0.0004

Data Index: 1231739 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0377. Min Act: -0.0004

Data Index: 1249424 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0349. Min Act: -0.0004

Data Index: 168252 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0349. Min Act: -0.0004

Data Index: 956767 (C4 (Web Text))

Max Activating Token Index: 885