Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1806 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0516. Min Act: -0.0005

Data Index: 717003 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0005

Data Index: 610757 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0497. Min Act: -0.0005

Data Index: 1261480 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0525. Min Act: -0.0005

Data Index: 1109943 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0508. Min Act: -0.0005

Data Index: 225067 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0491. Min Act: -0.0005

Data Index: 2805 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0483. Min Act: -0.0005

Data Index: 83465 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0465. Min Act: -0.0005

Data Index: 622383 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0504. Min Act: -0.0005

Data Index: 1335116 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0460. Min Act: -0.0005

Data Index: 249822 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0469. Min Act: -0.0005

Data Index: 1036878 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0461. Min Act: -0.0005

Data Index: 572643 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0468. Min Act: -0.0004

Data Index: 548149 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0457. Min Act: -0.0005

Data Index: 1205607 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0457. Min Act: -0.0005

Data Index: 1304121 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0446. Min Act: -0.0004

Data Index: 379780 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0445. Min Act: -0.0005

Data Index: 1220825 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0436. Min Act: -0.0005

Data Index: 808743 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0451. Min Act: -0.0005

Data Index: 1245444 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0453. Min Act: -0.0005

Data Index: 215715 (C4 (Web Text))

Max Activating Token Index: 508