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

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

Neuron 4551 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0143. Min Range: -4.0143

Max Act: 4.0143. Min Act: -0.0000

Data Index: 1610476 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.6518. Min Act: -0.0000

Data Index: 1625426 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.7810. Min Act: -0.0000

Data Index: 1514614 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.5813. Min Act: -0.0000

Data Index: 1552611 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.6435. Min Act: -0.0000

Data Index: 1508778 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.6275. Min Act: -0.0000

Data Index: 1484744 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.7462. Min Act: -0.0000

Data Index: 1621034 (Python Code)

Max Activating Token Index: 895

Text #7

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.5815. Min Act: -0.0000

Data Index: 1657002 (Python Code)

Max Activating Token Index: 43

Text #8

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.4670. Min Act: -0.0001

Data Index: 1565288 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.2714. Min Act: -0.0001

Data Index: 1593660 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.3495. Min Act: -0.0000

Data Index: 1555096 (Python Code)

Max Activating Token Index: 511

Text #11

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.3199. Min Act: -0.0001

Data Index: 1607921 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.1911. Min Act: -0.0001

Data Index: 1622018 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.4564. Min Act: -0.0000

Data Index: 1640660 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.2949. Min Act: -0.0001

Data Index: 1535808 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.3166. Min Act: -0.0000

Data Index: 1606732 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.1580. Min Act: -0.0000

Data Index: 1406668 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.3091. Min Act: -0.0001

Data Index: 1620576 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.2917. Min Act: -0.0001

Data Index: 1506633 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 4.0143. Min Range: -4.0143

Max Act: 3.2832. Min Act: -0.0000

Data Index: 1441712 (Python Code)

Max Activating Token Index: 736