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

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

Neuron 651 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0001

Data Index: 889261 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0873. Min Act: -0.0001

Data Index: 732373 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0907. Min Act: -0.0001

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1106695 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0806. Min Act: -0.0001

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0621. Min Act: -0.0000

Data Index: 319309 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1182967 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0751. Min Act: -0.0001

Data Index: 101486 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0753. Min Act: -0.0000

Data Index: 762006 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1105290 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0742. Min Act: -0.0001

Data Index: 94569 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0699. Min Act: -0.0001

Data Index: 763056 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1085293 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0658. Min Act: -0.0000

Data Index: 708303 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0658. Min Act: -0.0000

Data Index: 642546 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1078621 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0707. Min Act: -0.0001

Data Index: 539352 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1095064 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0623. Min Act: -0.0000

Data Index: 148126 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0598. Min Act: -0.0000

Data Index: 522620 (C4 (Web Text))

Max Activating Token Index: 214