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

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

Neuron 2679 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1785. Min Range: -3.1785

Max Act: 3.1785. Min Act: -0.0000

Data Index: 370101 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 3.1785. Min Range: -3.1785

Max Act: 3.0137. Min Act: -0.0000

Data Index: 295606 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 3.1785. Min Range: -3.1785

Max Act: 2.4935. Min Act: -0.0000

Data Index: 792923 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1188634 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.4608. Min Act: -0.0000

Data Index: 684203 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.3133. Min Act: -0.0000

Data Index: 625740 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1315634 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.0849. Min Act: -0.0000

Data Index: 274196 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.1091. Min Act: -0.0000

Data Index: 904903 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.1541. Min Act: -0.0000

Data Index: 765347 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.0094. Min Act: -0.0000

Data Index: 919770 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.0639. Min Act: -0.0000

Data Index: 278775 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.1785. Min Range: -3.1785

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1210531 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 3.1785. Min Range: -3.1785

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1219873 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 3.1785. Min Range: -3.1785

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1218196 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.1785. Min Range: -3.1785

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1171973 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 3.1785. Min Range: -3.1785

Max Act: 0.8322. Min Act: -0.0000

Data Index: 720084 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 3.1785. Min Range: -3.1785

Max Act: 0.7531. Min Act: -0.0000

Data Index: 581526 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 3.1785. Min Range: -3.1785

Max Act: 0.7699. Min Act: -0.0000

Data Index: 964133 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 3.1785. Min Range: -3.1785

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1248397 (C4 (Web Text))

Max Activating Token Index: 489