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

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

Neuron 659 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1106745 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9756. Min Act: -0.0000

Data Index: 591236 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0344. Min Act: -0.0000

Data Index: 526686 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1260613 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9809. Min Act: -0.0000

Data Index: 914397 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9736. Min Act: -0.0000

Data Index: 37567 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9745. Min Act: -0.0000

Data Index: 699107 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9676. Min Act: -0.0000

Data Index: 184671 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1269845 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9652. Min Act: -0.0000

Data Index: 590364 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0126. Min Act: -0.0000

Data Index: 697351 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1335420 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1331692 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9763. Min Act: -0.0000

Data Index: 830009 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9120. Min Act: -0.0000

Data Index: 366045 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9044. Min Act: -0.0000

Data Index: 447758 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8995. Min Act: -0.0000

Data Index: 15931 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8882. Min Act: -0.0000

Data Index: 699162 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1129096 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8845. Min Act: -0.0000

Data Index: 590025 (C4 (Web Text))

Max Activating Token Index: 221