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

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

Neuron 2847 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: 3.1871. Min Range: -3.1871

Max Act: 3.1871. Min Act: -0.0001

Data Index: 349708 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.1871. Min Range: -3.1871

Max Act: 3.1461. Min Act: -0.0001

Data Index: 613598 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 3.1871. Min Range: -3.1871

Max Act: 3.0397. Min Act: -0.0001

Data Index: 957032 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.9293. Min Act: -0.0000

Data Index: 156977 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.9261. Min Act: -0.0001

Data Index: 837562 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.9014. Min Act: -0.0000

Data Index: 972853 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.8271. Min Act: -0.0000

Data Index: 549555 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.5281. Min Act: -0.0001

Data Index: 436919 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.6542. Min Act: -0.0001

Data Index: 458082 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.9077. Min Act: -0.0001

Data Index: 1348843 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.7068. Min Act: -0.0001

Data Index: 494695 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.5708. Min Act: -0.0001

Data Index: 987327 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.7058. Min Act: -0.0001

Data Index: 623797 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.8167. Min Act: -0.0000

Data Index: 555102 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.7617. Min Act: -0.0001

Data Index: 208569 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.4786. Min Act: -0.0001

Data Index: 771687 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.4783. Min Act: -0.0000

Data Index: 957485 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.7141. Min Act: -0.0001

Data Index: 112847 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.5888. Min Act: -0.0000

Data Index: 815960 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 3.1871. Min Range: -3.1871

Max Act: 2.5626. Min Act: -0.0001

Data Index: 1110481 (C4 (Web Text))

Max Activating Token Index: 52