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

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

Neuron 4523 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4884. Min Range: -2.4884

Max Act: 2.4884. Min Act: -0.0000

Data Index: 1473843 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 2.4884. Min Range: -2.4884

Max Act: 2.0446. Min Act: -0.0000

Data Index: 1441693 (Python Code)

Max Activating Token Index: 85

Text #2

Max Range: 2.4884. Min Range: -2.4884

Max Act: 2.0224. Min Act: -0.0000

Data Index: 1600961 (Python Code)

Max Activating Token Index: 371

Text #3

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.9785. Min Act: -0.0000

Data Index: 1595920 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 2.4884. Min Range: -2.4884

Max Act: 2.0746. Min Act: -0.0000

Data Index: 1367439 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 2.4884. Min Range: -2.4884

Max Act: 2.0517. Min Act: -0.0000

Data Index: 1622177 (Python Code)

Max Activating Token Index: 603

Text #6

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.9954. Min Act: -0.0000

Data Index: 1412641 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1640696 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1561020 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1540705 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1616014 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1615062 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1476245 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1515990 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1405074 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1461977 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1512846 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1585333 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.8559. Min Act: -0.0000

Data Index: 1523574 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 2.4884. Min Range: -2.4884

Max Act: 1.7397. Min Act: -0.0000

Data Index: 1522158 (Python Code)

Max Activating Token Index: 21