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

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

Neuron 1687 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7300. Min Act: -0.0002

Data Index: 371269 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7219. Min Act: -0.0002

Data Index: 1076748 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6977. Min Act: -0.0002

Data Index: 525036 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6756. Min Act: -0.0002

Data Index: 166502 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6763. Min Act: -0.0002

Data Index: 664050 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6672. Min Act: -0.0002

Data Index: 1158288 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6562. Min Act: -0.0002

Data Index: 1333049 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6700. Min Act: -0.0002

Data Index: 1324003 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6511. Min Act: -0.0002

Data Index: 292079 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6547. Min Act: -0.0002

Data Index: 841629 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6607. Min Act: -0.0002

Data Index: 509049 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6405. Min Act: -0.0002

Data Index: 462568 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6516. Min Act: -0.0002

Data Index: 925902 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6485. Min Act: -0.0002

Data Index: 395970 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6415. Min Act: -0.0002

Data Index: 398188 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6405. Min Act: -0.0002

Data Index: 841543 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6256. Min Act: -0.0002

Data Index: 369559 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6365. Min Act: -0.0002

Data Index: 1226619 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6231. Min Act: -0.0002

Data Index: 858114 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6141. Min Act: -0.0002

Data Index: 711096 (C4 (Web Text))

Max Activating Token Index: 27