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

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

Neuron 4637 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: 2.5129. Min Range: -2.5129

Max Act: 2.5129. Min Act: -0.0000

Data Index: 327817 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 2.5129. Min Range: -2.5129

Max Act: 2.3237. Min Act: -0.0000

Data Index: 737804 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 2.5129. Min Range: -2.5129

Max Act: 2.2470. Min Act: -0.0001

Data Index: 530765 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 2.5129. Min Range: -2.5129

Max Act: 2.0395. Min Act: -0.0000

Data Index: 168439 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.8373. Min Act: -0.0000

Data Index: 317900 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 2.5129. Min Range: -2.5129

Max Act: 2.0015. Min Act: -0.0001

Data Index: 5843 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.9712. Min Act: -0.0001

Data Index: 408062 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.9381. Min Act: -0.0001

Data Index: 605678 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.8186. Min Act: -0.0000

Data Index: 933320 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.9187. Min Act: -0.0001

Data Index: 962691 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.9000. Min Act: -0.0000

Data Index: 766787 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1170116 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.7761. Min Act: -0.0000

Data Index: 412727 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.7989. Min Act: -0.0001

Data Index: 256035 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.8096. Min Act: -0.0001

Data Index: 366519 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.9949. Min Act: -0.0000

Data Index: 267931 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.7980. Min Act: -0.0000

Data Index: 593758 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.9061. Min Act: -0.0001

Data Index: 631969 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.8403. Min Act: -0.0000

Data Index: 1221512 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 2.5129. Min Range: -2.5129

Max Act: 1.7472. Min Act: -0.0000

Data Index: 158810 (C4 (Web Text))

Max Activating Token Index: 125