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

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

Neuron 4492 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5841. Min Act: -0.0000

Data Index: 344467 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1335088 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5621. Min Act: -0.0000

Data Index: 738374 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5491. Min Act: -0.0000

Data Index: 755336 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5362. Min Act: -0.0000

Data Index: 222113 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5568. Min Act: -0.0000

Data Index: 784548 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5169. Min Act: -0.0000

Data Index: 138944 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4973. Min Act: -0.0000

Data Index: 728504 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5096. Min Act: -0.0000

Data Index: 583136 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5676. Min Act: -0.0000

Data Index: 510990 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1324195 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1216380 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4763. Min Act: -0.0000

Data Index: 743053 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4350. Min Act: -0.0000

Data Index: 894395 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1291203 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4723. Min Act: -0.0000

Data Index: 923935 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4943. Min Act: -0.0000

Data Index: 877000 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.5192. Min Act: -0.0000

Data Index: 69016 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4806. Min Act: -0.0000

Data Index: 708366 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.5841. Min Range: -0.5841

Max Act: 0.4393. Min Act: 0.0000

Data Index: 1034702 (C4 (Web Text))

Max Activating Token Index: 370