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

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

Neuron 5729 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.8357. Min Act: -0.0000

Data Index: 1326221 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.7652. Min Act: -0.0000

Data Index: 856579 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.7006. Min Act: -0.0000

Data Index: 1189488 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.3230. Min Act: -0.0000

Data Index: 1052730 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.3583. Min Act: -0.0000

Data Index: 177207 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.4432. Min Act: -0.0000

Data Index: 1306825 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.0943. Min Act: -0.0000

Data Index: 844838 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.4031. Min Act: -0.0000

Data Index: 743067 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 3.8357. Min Range: -3.8357

Max Act: 2.9868. Min Act: -0.0000

Data Index: 759973 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.0748. Min Act: -0.0000

Data Index: 377043 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.0369. Min Act: -0.0000

Data Index: 699082 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.0334. Min Act: -0.0000

Data Index: 1538711 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 3.8357. Min Range: -3.8357

Max Act: 2.9536. Min Act: -0.0000

Data Index: 1109367 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.8357. Min Range: -3.8357

Max Act: 2.9367. Min Act: -0.0000

Data Index: 1105115 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 3.8357. Min Range: -3.8357

Max Act: 3.0398. Min Act: -0.0000

Data Index: 692410 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.8357. Min Range: -3.8357

Max Act: 2.7591. Min Act: -0.0000

Data Index: 1434596 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 3.8357. Min Range: -3.8357

Max Act: 2.7391. Min Act: -0.0000

Data Index: 440955 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 3.8357. Min Range: -3.8357

Max Act: 2.5238. Min Act: -0.0000

Data Index: 943791 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 3.8357. Min Range: -3.8357

Max Act: 2.7341. Min Act: -0.0000

Data Index: 1438417 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 3.8357. Min Range: -3.8357

Max Act: 2.8588. Min Act: -0.0000

Data Index: 898297 (C4 (Web Text))

Max Activating Token Index: 74