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

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

Neuron 898 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: 0.8084. Min Range: -0.8084

Max Act: 0.8084. Min Act: -0.0000

Data Index: 985123 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6972. Min Act: -0.0000

Data Index: 285662 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6711. Min Act: -0.0000

Data Index: 305559 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6740. Min Act: -0.0000

Data Index: 895734 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6932. Min Act: -0.0000

Data Index: 160977 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6742. Min Act: -0.0000

Data Index: 249543 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6269. Min Act: -0.0000

Data Index: 605464 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6339. Min Act: -0.0000

Data Index: 269094 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1239083 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6420. Min Act: -0.0000

Data Index: 434717 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6145. Min Act: -0.0000

Data Index: 238297 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6080. Min Act: -0.0000

Data Index: 848814 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6328. Min Act: -0.0000

Data Index: 304701 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5852. Min Act: -0.0000

Data Index: 225533 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5667. Min Act: -0.0000

Data Index: 363553 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5789. Min Act: -0.0000

Data Index: 28450 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1313630 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6011. Min Act: -0.0000

Data Index: 568209 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5465. Min Act: -0.0000

Data Index: 881716 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5393. Min Act: -0.0000

Data Index: 295515 (C4 (Web Text))

Max Activating Token Index: 624