Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1493 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.4077. Min Act: -0.0001

Data Index: 1508202 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3979. Min Act: -0.0001

Data Index: 1406255 (Python Code)

Max Activating Token Index: 349

Text #2

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1565262 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3732. Min Act: -0.0001

Data Index: 1542924 (Python Code)

Max Activating Token Index: 840

Text #4

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3727. Min Act: -0.0001

Data Index: 1361938 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3562. Min Act: -0.0001

Data Index: 1437617 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3456. Min Act: -0.0001

Data Index: 1501407 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3355. Min Act: -0.0001

Data Index: 1389544 (Python Code)

Max Activating Token Index: 141

Text #8

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3352. Min Act: -0.0001

Data Index: 1616011 (Python Code)

Max Activating Token Index: 650

Text #9

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3212. Min Act: -0.0001

Data Index: 1490001 (Python Code)

Max Activating Token Index: 810

Text #10

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1587173 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3196. Min Act: -0.0001

Data Index: 1447132 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2761. Min Act: -0.0001

Data Index: 1635340 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2938. Min Act: -0.0001

Data Index: 1475759 (Python Code)

Max Activating Token Index: 761

Text #14

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2764. Min Act: -0.0001

Data Index: 1519705 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1605619 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2547. Min Act: -0.0001

Data Index: 1376058 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2633. Min Act: -0.0001

Data Index: 1630224 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2692. Min Act: -0.0001

Data Index: 1451271 (Python Code)

Max Activating Token Index: 948

Text #19

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2642. Min Act: -0.0001

Data Index: 1586357 (Python Code)

Max Activating Token Index: 248