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

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

Neuron 466 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9592. Min Act: -0.0002

Data Index: 1300734 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9308. Min Act: -0.0002

Data Index: 1331792 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9400. Min Act: -0.0002

Data Index: 1180139 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9397. Min Act: -0.0002

Data Index: 1252155 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9059. Min Act: -0.0002

Data Index: 228124 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9119. Min Act: -0.0002

Data Index: 1106673 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8781. Min Act: -0.0002

Data Index: 1347089 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8744. Min Act: -0.0002

Data Index: 435854 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9021. Min Act: -0.0002

Data Index: 1280204 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8809. Min Act: -0.0002

Data Index: 252664 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8675. Min Act: -0.0002

Data Index: 468486 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8614. Min Act: -0.0002

Data Index: 532210 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8544. Min Act: -0.0002

Data Index: 707886 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8535. Min Act: -0.0002

Data Index: 400459 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8653. Min Act: -0.0002

Data Index: 1276393 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8487. Min Act: -0.0002

Data Index: 695056 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8284. Min Act: -0.0002

Data Index: 540521 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8386. Min Act: -0.0002

Data Index: 768945 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8516. Min Act: -0.0002

Data Index: 1315315 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8323. Min Act: -0.0002

Data Index: 1283601 (C4 (Web Text))

Max Activating Token Index: 9