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

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

Neuron 1162 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7767. Min Act: -0.0000

Data Index: 11607 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7762. Min Act: -0.0000

Data Index: 470125 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7664. Min Act: -0.0000

Data Index: 48080 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7217. Min Act: -0.0000

Data Index: 762157 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1236344 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6757. Min Act: -0.0000

Data Index: 5844 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6693. Min Act: -0.0000

Data Index: 886137 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6785. Min Act: -0.0000

Data Index: 870081 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6689. Min Act: -0.0000

Data Index: 375180 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6538. Min Act: -0.0000

Data Index: 227061 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6598. Min Act: -0.0000

Data Index: 631180 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1273434 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6656. Min Act: -0.0000

Data Index: 538877 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6909. Min Act: -0.0000

Data Index: 164498 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5716. Min Act: -0.0000

Data Index: 678220 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6372. Min Act: -0.0000

Data Index: 543301 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6154. Min Act: -0.0000

Data Index: 856368 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5774. Min Act: -0.0000

Data Index: 846506 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6175. Min Act: -0.0000

Data Index: 287179 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6109. Min Act: -0.0000

Data Index: 100204 (C4 (Web Text))

Max Activating Token Index: 858