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

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

Neuron 2799 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.7771. Min Act: -0.0001

Data Index: 1628632 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.4551. Min Act: -0.0001

Data Index: 1643727 (Python Code)

Max Activating Token Index: 456

Text #2

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.6498. Min Act: -0.0001

Data Index: 1363989 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.4716. Min Act: -0.0001

Data Index: 1400659 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.4640. Min Act: -0.0001

Data Index: 1543697 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.3683. Min Act: -0.0000

Data Index: 1534804 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.3103. Min Act: -0.0000

Data Index: 1510241 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.3159. Min Act: -0.0001

Data Index: 1372720 (Python Code)

Max Activating Token Index: 82

Text #8

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.2611. Min Act: -0.0001

Data Index: 1598100 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.1662. Min Act: -0.0000

Data Index: 1562671 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.1531. Min Act: -0.0001

Data Index: 1481990 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.2009. Min Act: -0.0001

Data Index: 1540342 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.1752. Min Act: -0.0001

Data Index: 1493628 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.1765. Min Act: -0.0000

Data Index: 1419220 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.1320. Min Act: -0.0000

Data Index: 1363155 (Python Code)

Max Activating Token Index: 293

Text #15

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.0722. Min Act: -0.0001

Data Index: 1606909 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.1195. Min Act: -0.0000

Data Index: 1523988 (Python Code)

Max Activating Token Index: 33

Text #17

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.1111. Min Act: -0.0001

Data Index: 1431813 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 3.7771. Min Range: -3.7771

Max Act: 1.9499. Min Act: -0.0001

Data Index: 1434579 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.1103. Min Act: -0.0000

Data Index: 1471578 (Python Code)

Max Activating Token Index: 20