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

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

Neuron 1363 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: 1.2304. Min Range: -1.2304

Max Act: 1.2304. Min Act: -0.0001

Data Index: 1418455 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.9480. Min Act: -0.0001

Data Index: 1643053 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.7652. Min Act: -0.0001

Data Index: 1649993 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.7548. Min Act: -0.0001

Data Index: 1411708 (Python Code)

Max Activating Token Index: 492

Text #4

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.7027. Min Act: -0.0001

Data Index: 1476993 (Python Code)

Max Activating Token Index: 84

Text #5

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6793. Min Act: -0.0002

Data Index: 1652448 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6872. Min Act: -0.0001

Data Index: 1377928 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6809. Min Act: -0.0001

Data Index: 1428082 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6707. Min Act: -0.0001

Data Index: 1544415 (Python Code)

Max Activating Token Index: 47

Text #9

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6714. Min Act: -0.0001

Data Index: 1482609 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6689. Min Act: -0.0001

Data Index: 1627086 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1625140 (Python Code)

Max Activating Token Index: 781

Text #12

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6611. Min Act: -0.0001

Data Index: 1381648 (Python Code)

Max Activating Token Index: 174

Text #13

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6621. Min Act: -0.0001

Data Index: 1559871 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1646803 (Python Code)

Max Activating Token Index: 390

Text #15

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6507. Min Act: -0.0001

Data Index: 1397741 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6173. Min Act: -0.0001

Data Index: 1543449 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6281. Min Act: -0.0001

Data Index: 1643154 (Python Code)

Max Activating Token Index: 572

Text #18

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.6155. Min Act: -0.0001

Data Index: 1481199 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 1.2304. Min Range: -1.2304

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1574246 (Python Code)

Max Activating Token Index: 50