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

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

Neuron 3068 in Layer 0

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: 0.6182. Min Range: -0.6182

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1634081 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5811. Min Act: -0.0001

Data Index: 1606920 (Python Code)

Max Activating Token Index: 761

Text #2

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5953. Min Act: -0.0001

Data Index: 1569784 (Python Code)

Max Activating Token Index: 589

Text #3

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5688. Min Act: -0.0001

Data Index: 1612246 (Python Code)

Max Activating Token Index: 612

Text #4

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5691. Min Act: -0.0001

Data Index: 1454329 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5621. Min Act: -0.0001

Data Index: 1541616 (Python Code)

Max Activating Token Index: 734

Text #6

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5740. Min Act: -0.0001

Data Index: 1485904 (Python Code)

Max Activating Token Index: 137

Text #7

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5723. Min Act: -0.0001

Data Index: 1619511 (Python Code)

Max Activating Token Index: 514

Text #8

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5585. Min Act: -0.0001

Data Index: 1530367 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5641. Min Act: -0.0001

Data Index: 1519550 (Python Code)

Max Activating Token Index: 388

Text #10

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5596. Min Act: -0.0001

Data Index: 1423610 (Python Code)

Max Activating Token Index: 712

Text #11

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5535. Min Act: -0.0002

Data Index: 1635925 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5570. Min Act: -0.0001

Data Index: 1595359 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5408. Min Act: -0.0001

Data Index: 1413236 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5448. Min Act: -0.0001

Data Index: 1472545 (Python Code)

Max Activating Token Index: 687

Text #15

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5306. Min Act: -0.0001

Data Index: 1634905 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5308. Min Act: -0.0001

Data Index: 1494360 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5400. Min Act: -0.0001

Data Index: 1396608 (Python Code)

Max Activating Token Index: 790

Text #18

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5304. Min Act: -0.0001

Data Index: 1450830 (Python Code)

Max Activating Token Index: 314

Text #19

Max Range: 0.6182. Min Range: -0.6182

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1635698 (Python Code)

Max Activating Token Index: 428