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

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

Neuron 5830 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5083. Min Range: -1.5083

Max Act: 1.5083. Min Act: -0.0000

Data Index: 586615 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 1.5083. Min Range: -1.5083

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1641145 (Python Code)

Max Activating Token Index: 465

Text #2

Max Range: 1.5083. Min Range: -1.5083

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1349006 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.5083. Min Range: -1.5083

Max Act: 1.1359. Min Act: -0.0000

Data Index: 211096 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 1.5083. Min Range: -1.5083

Max Act: 1.1036. Min Act: -0.0000

Data Index: 239266 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.5083. Min Range: -1.5083

Max Act: 1.0297. Min Act: -0.0000

Data Index: 785109 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9184. Min Act: -0.0000

Data Index: 240809 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1413410 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1421368 (Python Code)

Max Activating Token Index: 644

Text #9

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9676. Min Act: -0.0000

Data Index: 49885 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9502. Min Act: -0.0000

Data Index: 349771 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9320. Min Act: -0.0000

Data Index: 50135 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9613. Min Act: -0.0000

Data Index: 120985 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1190862 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1535952 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.8129. Min Act: -0.0000

Data Index: 863095 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1060350 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.8623. Min Act: -0.0000

Data Index: 570537 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.9381. Min Act: -0.0000

Data Index: 138243 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.5083. Min Range: -1.5083

Max Act: 0.8523. Min Act: -0.0000

Data Index: 696326 (C4 (Web Text))

Max Activating Token Index: 508