Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3184 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.8968. Min Act: -0.0000

Data Index: 429920 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7615. Min Act: -0.0000

Data Index: 926818 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1036413 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7517. Min Act: -0.0000

Data Index: 458071 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7402. Min Act: -0.0000

Data Index: 892146 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7396. Min Act: -0.0000

Data Index: 214685 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7295. Min Act: 0.0002

Data Index: 571523 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7032. Min Act: -0.0000

Data Index: 236341 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1305922 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6681. Min Act: -0.0000

Data Index: 47336 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6848. Min Act: -0.0000

Data Index: 613995 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6762. Min Act: -0.0000

Data Index: 301533 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6861. Min Act: -0.0000

Data Index: 267000 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1333254 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1033140 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1349640 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6620. Min Act: 0.0001

Data Index: 1120613 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6426. Min Act: -0.0000

Data Index: 938174 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6692. Min Act: -0.0000

Data Index: 261388 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6225. Min Act: -0.0000

Data Index: 639092 (C4 (Web Text))

Max Activating Token Index: 226