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

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

Neuron 1702 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0079. Min Range: -1.0079

Max Act: 1.0079. Min Act: -0.0001

Data Index: 1608060 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9182. Min Act: -0.0001

Data Index: 1372745 (Python Code)

Max Activating Token Index: 800

Text #2

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9603. Min Act: -0.0001

Data Index: 1612796 (Python Code)

Max Activating Token Index: 123

Text #3

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9101. Min Act: -0.0001

Data Index: 1525374 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9069. Min Act: -0.0001

Data Index: 1388169 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8787. Min Act: -0.0001

Data Index: 1591416 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8751. Min Act: -0.0001

Data Index: 1587085 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1492637 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8936. Min Act: -0.0001

Data Index: 1621287 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8313. Min Act: -0.0001

Data Index: 1544630 (Python Code)

Max Activating Token Index: 44

Text #10

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8308. Min Act: -0.0001

Data Index: 1548031 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8265. Min Act: -0.0001

Data Index: 1611234 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8484. Min Act: -0.0001

Data Index: 1635838 (Python Code)

Max Activating Token Index: 258

Text #13

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8359. Min Act: -0.0001

Data Index: 1392372 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1409588 (Python Code)

Max Activating Token Index: 103

Text #15

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7895. Min Act: -0.0001

Data Index: 1491421 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7934. Min Act: -0.0001

Data Index: 1562588 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7774. Min Act: -0.0001

Data Index: 1588384 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8049. Min Act: -0.0001

Data Index: 1405558 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7944. Min Act: -0.0001

Data Index: 1530459 (Python Code)

Max Activating Token Index: 25