Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1372383 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1362669 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1462697 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1608498 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1479269 (Python Code)

Max Activating Token Index: 694

Text #5

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1618712 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1612394 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1508696 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1639179 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1430251 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5885. Min Act: -0.0000

Data Index: 276161 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1624509 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1609072 (Python Code)

Max Activating Token Index: 495

Text #13

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1445564 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1419010 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1625284 (Python Code)

Max Activating Token Index: 840

Text #16

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1551969 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1397031 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1475785 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1365319 (Python Code)

Max Activating Token Index: 861